BM25

lexical

All results produced by QueryGym · fully reproducible!

40 method × LLM configurations using this retriever across BEIR, MS MARCO DL, and DL-HARD.
Click any row or the + button to expand. Tabs switch dataset context. The three steps (reformulate → retrieve → evaluate) update accordingly.

	Method	LLM	ArguAna		DBPedia		FiQA		SciFact		COVID		News		BRIGHT — AOPS		BRIGHT — Biology		BRIGHT — Earth Science		BRIGHT — Economics		BRIGHT — LeetCode		BRIGHT — Pony		BRIGHT — Psychology		BRIGHT — Robotics		BRIGHT — Stack Overflow		BRIGHT — Sustainable Living		BRIGHT — TheoremQA Questions		BRIGHT — TheoremQA Theorems		DL-HARD		DL 2019		DL 2020
	Method	LLM	nDCG@10	R@100	nDCG@10	R@100	nDCG@10	R@100	nDCG@10	R@100	nDCG@10	R@100	nDCG@10	R@100																									nDCG@10	R@1k	nDCG@10	R@1k	nDCG@10	R@1k
	csqe	Qwen2.5-72B-Instruct	0.3864	—	0.3556	0.4639	0.2132	—	0.7141	—	0.6716	0.1491	0.3861	0.4892	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	0.2848	0.6998	0.6391	0.8608	0.5606	0.8603
methodcsqe llmQwen2.5-72B-Instruct retrieverBM25 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-arguana \ --method csqe \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-arguana.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 \ beir-v1.0.0-arguana-test run.txt Run id 6e44c9a23591ec9a · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-dbpedia-entity \ --method csqe \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-dbpedia-entity.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-dbpedia-entity-test run.txt Run id 43e3c6b01609e6f0 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-fiqa \ --method csqe \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-fiqa.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 \ beir-v1.0.0-fiqa-test run.txt Run id be5818c6d67a2fc3 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-scifact \ --method csqe \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-scifact.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 \ beir-v1.0.0-scifact-test run.txt Run id 07f8082534b1b82c · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-covid \ --method csqe \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-covid.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-covid-test run.txt Run id a04f3be704b59a99 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-news \ --method csqe \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-news.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-news-test run.txt Run id 7cc031ceec7f22cd · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.dlhard \ --method csqe \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ /mnt/data/son/Thesis/t5/data/dlhard/neutral_queries.tsv run.txt Run id 374d868e8c9d9b43 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2019 \ --method csqe \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl19-passage run.txt Run id 239707be9e6e9d0b · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2020 \ --method csqe \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl20-passage run.txt Run id 4d261dda4cfb7038 · open full run detail →
	csqe	Qwen2.5-7B-Instruct	0.4008	0.9403	0.3767	0.5078	0.2200	0.5466	0.7183	0.9543	0.6757	0.1600	0.4504	0.5795	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	0.3322	0.7913	0.6873	0.8921	0.6083	0.8596
methodcsqe llmQwen2.5-7B-Instruct retrieverBM25 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-arguana \ --method csqe \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-arguana.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-arguana-test run.txt Run id a4b96e532713cf8c · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-dbpedia-entity \ --method csqe \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-dbpedia-entity.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-dbpedia-entity-test run.txt Run id 45f75d3dda634e3d · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-fiqa \ --method csqe \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-fiqa.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-fiqa-test run.txt Run id 86d33a6522c7bf66 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-scifact \ --method csqe \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-scifact.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-scifact-test run.txt Run id ed3f091219373725 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-covid \ --method csqe \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-covid.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-covid-test run.txt Run id 46831c7ce6869053 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-news \ --method csqe \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-news.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-news-test run.txt Run id 0966213446c0caca · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.dlhard \ --method csqe \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ /mnt/data/son/Thesis/t5/data/dlhard/neutral_queries.tsv run.txt Run id a669e73a9f865bf9 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2019 \ --method csqe \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"zs","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl19-passage run.txt Run id 001ab6762f99c6b6 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2020 \ --method csqe \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl20-passage run.txt Run id 2b82b2cea4817e13 · open full run detail →
	csqe	gpt-4.1	0.3977	0.9445	0.3899	0.5136	0.2473	0.5835	0.7206	0.9487	0.6994	0.1638	0.4790	0.5909	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	0.3658	0.7873	0.6899	0.9035	0.6548	0.8871
methodcsqe llmgpt-4.1 retrieverBM25 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-arguana \ --method csqe \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-arguana.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-arguana-test run.txt Run id 2f7746328604d0bc · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-dbpedia-entity \ --method csqe \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-dbpedia-entity.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-dbpedia-entity-test run.txt Run id 8b352f15c35044e7 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-fiqa \ --method csqe \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-fiqa.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-fiqa-test run.txt Run id 52902b5453f351e6 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-scifact \ --method csqe \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-scifact.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-scifact-test run.txt Run id b6b8168e2872eb9b · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-covid \ --method csqe \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-covid.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-covid-test run.txt Run id 6fcfefc44e3d3a4c · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-news \ --method csqe \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-news.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-news-test run.txt Run id d53af0d617c5b9be · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.dlhard \ --method csqe \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ /mnt/data/son/Thesis/t5/data/dlhard/neutral_queries.tsv run.txt Run id ede9af17c87e4322 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2019 \ --method csqe \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl19-passage run.txt Run id 0411fc9a522f86b1 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2020 \ --method csqe \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl20-passage run.txt Run id a0441e8e51b3a613 · open full run detail →
	csqe	gpt-4.1-nano	0.3964	0.9381	0.3647	0.4939	0.2401	0.5553	0.7099	0.9587	0.6171	0.1543	0.4271	0.5221	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	0.2436	0.7327	0.5410	0.8221	0.5142	0.8586
methodcsqe llmgpt-4.1-nano retrieverBM25 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-arguana \ --method csqe \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-arguana.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-arguana-test run.txt Run id f32e376e0f39d46f · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-dbpedia-entity \ --method csqe \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-dbpedia-entity.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-dbpedia-entity-test run.txt Run id bb094947e62ff61f · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-fiqa \ --method csqe \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-fiqa.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-fiqa-test run.txt Run id 44d2d2aef166eb33 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-scifact \ --method csqe \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-scifact.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-scifact-test run.txt Run id a7a782bb19e2ca65 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-covid \ --method csqe \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-covid.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-covid-test run.txt Run id 46eb796f1598bbf8 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-news \ --method csqe \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-news.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-news-test run.txt Run id 4c83d57b9282b0b6 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.dlhard \ --method csqe \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ /mnt/data/son/Thesis/t5/data/dlhard/neutral_queries.tsv run.txt Run id 6685bbc537e4cd4e · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2019 \ --method csqe \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl19-passage run.txt Run id 4b8155969a7b03e2 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2020 \ --method csqe \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl20-passage run.txt Run id ce48ec0f783ddd1c · open full run detail →
	genqr	Qwen2.5-72B-Instruct	0.4188	—	0.2649	0.3941	0.1725	—	0.6976	—	0.6129	0.1349	0.4003	0.5838	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	0.2091	0.6822	0.4198	0.7616	0.4238	0.7919
methodgenqr llmQwen2.5-72B-Instruct retrieverBM25 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-arguana \ --method genqr \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-arguana.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 \ beir-v1.0.0-arguana-test run.txt Run id e8335322dca5be04 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-dbpedia-entity \ --method genqr \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-dbpedia-entity.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-dbpedia-entity-test run.txt Run id 9de683664800281a · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-fiqa \ --method genqr \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-fiqa.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 \ beir-v1.0.0-fiqa-test run.txt Run id e7d00fc2eb056b9f · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-scifact \ --method genqr \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-scifact.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 \ beir-v1.0.0-scifact-test run.txt Run id 72b99b02937d8708 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-covid \ --method genqr \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-covid.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-covid-test run.txt Run id e305bab14adcf270 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-news \ --method genqr \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-news.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-news-test run.txt Run id 93c6977e1b1e6a0d · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.dlhard \ --method genqr \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ /mnt/data/son/Thesis/t5/data/dlhard/neutral_queries.tsv run.txt Run id 6a6303729251dfe7 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2019 \ --method genqr \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl19-passage run.txt Run id fe245d46cfc2b226 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2020 \ --method genqr \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl20-passage run.txt Run id 9bc21a52ef2dd34c · open full run detail →
	genqr	Qwen2.5-7B-Instruct	0.4339	0.9523	0.2876	0.4203	0.2041	0.5057	0.6919	0.9413	0.6523	0.1522	0.4295	0.5580	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	0.2006	0.6458	0.4334	0.7860	0.3857	0.7740
methodgenqr llmQwen2.5-7B-Instruct retrieverBM25 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-arguana \ --method genqr \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-arguana.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-arguana-test run.txt Run id 817c54fef880fca4 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-dbpedia-entity \ --method genqr \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-dbpedia-entity.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-dbpedia-entity-test run.txt Run id 531a793785efac05 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-fiqa \ --method genqr \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-fiqa.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-fiqa-test run.txt Run id 881e0abf3b724af9 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-scifact \ --method genqr \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-scifact.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-scifact-test run.txt Run id e0436df6d059f504 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-covid \ --method genqr \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-covid.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-covid-test run.txt Run id fcf3c5eebc8142eb · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-news \ --method genqr \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-news.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-news-test run.txt Run id 9c3073daddc881ec · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.dlhard \ --method genqr \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"variants","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ /mnt/data/son/Thesis/t5/data/dlhard/neutral_queries.tsv run.txt Run id e80f5421465393eb · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2019 \ --method genqr \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"variants","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl19-passage run.txt Run id 0a66258aa59131ae · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2020 \ --method genqr \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"variants","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl20-passage run.txt Run id 8a3ae62556bd13a7 · open full run detail →
	genqr	gpt-4.1	0.4060	0.9495	0.3442	0.4635	0.2302	0.5818	0.7262	0.9632	0.6869	0.1627	0.4647	0.6096	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	0.2921	0.7434	0.5479	0.8282	0.5368	0.8402
methodgenqr llmgpt-4.1 retrieverBM25 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-arguana \ --method genqr \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-arguana.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-arguana-test run.txt Run id 0a2206f04f384f1b · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-dbpedia-entity \ --method genqr \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-dbpedia-entity.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-dbpedia-entity-test run.txt Run id a65e64f2254e844f · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-fiqa \ --method genqr \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-fiqa.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-fiqa-test run.txt Run id f929036fa0637430 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-scifact \ --method genqr \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-scifact.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-scifact-test run.txt Run id 9aa87cc50d157aaa · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-covid \ --method genqr \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-covid.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-covid-test run.txt Run id a9f346f8ca12ff11 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-news \ --method genqr \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-news.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-news-test run.txt Run id 1c66ed36ae4763d8 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.dlhard \ --method genqr \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ /mnt/data/son/Thesis/t5/data/dlhard/neutral_queries.tsv run.txt Run id 0ae7a189f978dc05 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2019 \ --method genqr \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl19-passage run.txt Run id 7ce35ece3f5738e6 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2020 \ --method genqr \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl20-passage run.txt Run id 50e940a6235068dc · open full run detail →
	genqr	gpt-4.1-nano	0.4013	0.9488	0.2591	0.4137	0.1974	0.5142	0.7011	0.9566	0.6662	0.1561	0.4251	0.5834	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	0.1743	0.6575	0.4389	0.7360	0.4302	0.7701
methodgenqr llmgpt-4.1-nano retrieverBM25 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-arguana \ --method genqr \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-arguana.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-arguana-test run.txt Run id 2c4406046b14c5ce · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-dbpedia-entity \ --method genqr \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-dbpedia-entity.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-dbpedia-entity-test run.txt Run id d8d4435d005efe36 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-fiqa \ --method genqr \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-fiqa.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-fiqa-test run.txt Run id 836b8495c480ccef · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-scifact \ --method genqr \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-scifact.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-scifact-test run.txt Run id 638e203d05b899e7 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-covid \ --method genqr \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-covid.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-covid-test run.txt Run id 964de7307d7868b3 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-news \ --method genqr \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-news.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-news-test run.txt Run id 04381254719bf3ab · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.dlhard \ --method genqr \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ /mnt/data/son/Thesis/t5/data/dlhard/neutral_queries.tsv run.txt Run id 17a6068f238ed7a6 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2019 \ --method genqr \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl19-passage run.txt Run id c8a5a2d5dc9b8cb4 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2020 \ --method genqr \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl20-passage run.txt Run id 013d7a240090b3b9 · open full run detail →
	genqr_ensemble	Qwen2.5-72B-Instruct	0.4080	—	0.3136	0.4161	0.2061	—	0.7089	—	0.6437	0.1451	0.4080	0.5923	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	0.2463	0.6975	0.4739	0.7999	0.4248	0.7820
methodgenqr_ensemble llmQwen2.5-72B-Instruct retrieverBM25 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-arguana \ --method genqr_ensemble \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-arguana.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 \ beir-v1.0.0-arguana-test run.txt Run id 73a94ecc826455b3 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-dbpedia-entity \ --method genqr_ensemble \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-dbpedia-entity.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-dbpedia-entity-test run.txt Run id abd50579fccb6cff · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-fiqa \ --method genqr_ensemble \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-fiqa.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 \ beir-v1.0.0-fiqa-test run.txt Run id 2c456eb00d9d2c89 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-scifact \ --method genqr_ensemble \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-scifact.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 \ beir-v1.0.0-scifact-test run.txt Run id 59b04f1a88a63ec9 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-covid \ --method genqr_ensemble \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-covid.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-covid-test run.txt Run id ddab8adddb1ab66e · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-news \ --method genqr_ensemble \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-news.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-news-test run.txt Run id 42284a01f5419323 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.dlhard \ --method genqr_ensemble \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ /mnt/data/son/Thesis/t5/data/dlhard/neutral_queries.tsv run.txt Run id d08cbd7ce239e045 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2019 \ --method genqr_ensemble \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl19-passage run.txt Run id 5cd6ab2d47e8224a · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2020 \ --method genqr_ensemble \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl20-passage run.txt Run id 14bb031ca7ba3d45 · open full run detail →
	genqr_ensemble	Qwen2.5-7B-Instruct	0.4187	0.9566	0.3464	0.4916	0.2075	0.5114	0.7035	0.9476	0.6780	0.1745	0.4367	0.6031	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	0.2429	0.7210	0.4512	0.7952	0.4896	0.8164
methodgenqr_ensemble llmQwen2.5-7B-Instruct retrieverBM25 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-arguana \ --method genqr_ensemble \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-arguana.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-arguana-test run.txt Run id e49dd54b6f58c3cd · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-dbpedia-entity \ --method genqr_ensemble \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-dbpedia-entity.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-dbpedia-entity-test run.txt Run id e5190f2e71794feb · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-fiqa \ --method genqr_ensemble \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-fiqa.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-fiqa-test run.txt Run id 3070244b6a934e3e · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-scifact \ --method genqr_ensemble \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-scifact.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-scifact-test run.txt Run id fdd2a2c42bfdd898 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-covid \ --method genqr_ensemble \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-covid.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-covid-test run.txt Run id d24edd01bf1e0629 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-news \ --method genqr_ensemble \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-news.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-news-test run.txt Run id babe70f0dbdbc64c · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.dlhard \ --method genqr_ensemble \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"variants","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ /mnt/data/son/Thesis/t5/data/dlhard/neutral_queries.tsv run.txt Run id 7c2a243a2ffb9ede · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2019 \ --method genqr_ensemble \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl19-passage run.txt Run id e94186b450bd891b · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2020 \ --method genqr_ensemble \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"variants","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl20-passage run.txt Run id fb64d41cd58d8e73 · open full run detail →
	genqr_ensemble	gpt-4.1	0.4073	0.9566	0.3600	0.4765	0.2388	0.5804	0.7251	0.9666	0.7528	0.1839	0.4860	0.6293	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	0.2697	0.7775	0.5589	0.8685	0.5528	0.8613
methodgenqr_ensemble llmgpt-4.1 retrieverBM25 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-arguana \ --method genqr_ensemble \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-arguana.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-arguana-test run.txt Run id 3265894a06d11b4c · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-dbpedia-entity \ --method genqr_ensemble \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-dbpedia-entity.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-dbpedia-entity-test run.txt Run id 2e61f53146f09717 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-fiqa \ --method genqr_ensemble \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-fiqa.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-fiqa-test run.txt Run id bcca7b56a3366e0c · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-scifact \ --method genqr_ensemble \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-scifact.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-scifact-test run.txt Run id 2d91700b15f7295e · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-covid \ --method genqr_ensemble \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-covid.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-covid-test run.txt Run id c3538629baabb960 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-news \ --method genqr_ensemble \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-news.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-news-test run.txt Run id 3da136bf80ceae3f · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.dlhard \ --method genqr_ensemble \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ /mnt/data/son/Thesis/t5/data/dlhard/neutral_queries.tsv run.txt Run id 567a1e2e134b7f43 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2019 \ --method genqr_ensemble \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl19-passage run.txt Run id 3e80d06ca2463140 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2020 \ --method genqr_ensemble \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl20-passage run.txt Run id 4f46997304478552 · open full run detail →
	genqr_ensemble	gpt-4.1-nano	0.3945	0.9474	0.3181	0.4501	0.1972	0.5205	0.7034	0.9626	0.6884	0.1690	0.4349	0.6199	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	0.2154	0.6990	0.4579	0.8217	0.4718	0.8158
methodgenqr_ensemble llmgpt-4.1-nano retrieverBM25 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-arguana \ --method genqr_ensemble \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-arguana.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-arguana-test run.txt Run id 53c695c1305ea59f · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-dbpedia-entity \ --method genqr_ensemble \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-dbpedia-entity.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-dbpedia-entity-test run.txt Run id 774e8de39872c7d7 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-fiqa \ --method genqr_ensemble \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-fiqa.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-fiqa-test run.txt Run id 08dc7eee4fe281ec · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-scifact \ --method genqr_ensemble \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-scifact.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-scifact-test run.txt Run id babbac40e9ebdff2 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-covid \ --method genqr_ensemble \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-covid.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-covid-test run.txt Run id e7500118bc202a15 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-news \ --method genqr_ensemble \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-news.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-news-test run.txt Run id ada93fa3b5ae8c60 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.dlhard \ --method genqr_ensemble \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ /mnt/data/son/Thesis/t5/data/dlhard/neutral_queries.tsv run.txt Run id 9f5013e90fe58d17 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2019 \ --method genqr_ensemble \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl19-passage run.txt Run id d05a1a92ddcada7b · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2020 \ --method genqr_ensemble \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl20-passage run.txt Run id 8e77272eeb2933bd · open full run detail →
	lamer	Qwen2.5-72B-Instruct	0.4111	—	0.4010	0.5217	0.2395	—	0.7251	—	0.7240	0.1667	0.4677	0.6105	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	0.3635	0.7820	0.6651	0.8666	0.6711	0.8920
methodlamer llmQwen2.5-72B-Instruct retrieverBM25 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-arguana \ --method lamer \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-arguana.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 \ beir-v1.0.0-arguana-test run.txt Run id 3ba08ce1abc4801d · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-dbpedia-entity \ --method lamer \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-dbpedia-entity.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-dbpedia-entity-test run.txt Run id 36de53b6918e215b · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-fiqa \ --method lamer \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-fiqa.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 \ beir-v1.0.0-fiqa-test run.txt Run id bea836bea41c6a84 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-scifact \ --method lamer \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-scifact.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 \ beir-v1.0.0-scifact-test run.txt Run id 985c2f9474647b53 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-covid \ --method lamer \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-covid.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-covid-test run.txt Run id e91e6a2bee960c7c · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-news \ --method lamer \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-news.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-news-test run.txt Run id 74a12b2d72abe529 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.dlhard \ --method lamer \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ /mnt/data/son/Thesis/t5/data/dlhard/neutral_queries.tsv run.txt Run id fc152cc80664915c · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2019 \ --method lamer \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl19-passage run.txt Run id 68be0320c3759961 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2020 \ --method lamer \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl20-passage run.txt Run id 1cb1eb5085c84489 · open full run detail →
	lamer	Qwen2.5-7B-Instruct	0.4063	0.9388	0.3896	0.5139	0.2337	0.5558	0.7140	0.9593	0.6955	0.1704	0.4424	0.5960	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	0.3570	0.7633	0.6602	0.8553	0.6322	0.8933
methodlamer llmQwen2.5-7B-Instruct retrieverBM25 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-arguana \ --method lamer \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-arguana.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-arguana-test run.txt Run id 78a09817091818d1 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-dbpedia-entity \ --method lamer \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-dbpedia-entity.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-dbpedia-entity-test run.txt Run id d86dc93cb8e496dc · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-fiqa \ --method lamer \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-fiqa.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-fiqa-test run.txt Run id 4ae79ecd932684fd · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-scifact \ --method lamer \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-scifact.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-scifact-test run.txt Run id eb8c999ba4df568e · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-covid \ --method lamer \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-covid.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-covid-test run.txt Run id ffeb0dbe30c15130 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-news \ --method lamer \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-news.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-news-test run.txt Run id 191f3146ee820605 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.dlhard \ --method lamer \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ /mnt/data/son/Thesis/t5/data/dlhard/neutral_queries.tsv run.txt Run id 2887a055720c6629 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2019 \ --method lamer \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl19-passage run.txt Run id 67f45dc24ca2c49b · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2020 \ --method lamer \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl20-passage run.txt Run id 4d996428a216f673 · open full run detail →
	lamer	gpt-4.1	0.4119	0.9452	0.3989	0.5159	0.2616	0.5901	0.7253	0.9487	0.7020	0.1661	0.4799	0.5960	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	0.3555	0.8065	0.6368	0.8566	0.6530	0.9002
methodlamer llmgpt-4.1 retrieverBM25 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-arguana \ --method lamer \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-arguana.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-arguana-test run.txt Run id bcffbda0dd6fdc12 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-dbpedia-entity \ --method lamer \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-dbpedia-entity.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-dbpedia-entity-test run.txt Run id eaec077abfaf854a · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-fiqa \ --method lamer \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-fiqa.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-fiqa-test run.txt Run id 687ae132065e0b45 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-scifact \ --method lamer \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-scifact.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-scifact-test run.txt Run id f51fc1481896b8bc · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-covid \ --method lamer \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-covid.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-covid-test run.txt Run id 0a644ef98cc95b6f · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-news \ --method lamer \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-news.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-news-test run.txt Run id 6a0e18727969f9d2 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.dlhard \ --method lamer \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ /mnt/data/son/Thesis/t5/data/dlhard/neutral_queries.tsv run.txt Run id aa3971fcc285abde · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2019 \ --method lamer \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl19-passage run.txt Run id 63c3ce02ce9a2f14 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2020 \ --method lamer \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl20-passage run.txt Run id 8d328e3c1ae63cfa · open full run detail →
	lamer	gpt-4.1-nano	0.4037	0.9388	0.3440	0.4807	0.2360	0.5449	0.7220	0.9393	0.6721	0.1748	0.4328	0.5575	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	0.3398	0.7697	0.6731	0.8548	0.6560	0.8865
methodlamer llmgpt-4.1-nano retrieverBM25 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-arguana \ --method lamer \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-arguana.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-arguana-test run.txt Run id 80fe25ed5bf87022 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-dbpedia-entity \ --method lamer \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-dbpedia-entity.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-dbpedia-entity-test run.txt Run id 8aac783cbbebdffe · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-fiqa \ --method lamer \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-fiqa.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-fiqa-test run.txt Run id 03941802197741ee · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-scifact \ --method lamer \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-scifact.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-scifact-test run.txt Run id e6250cabff57cb42 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-covid \ --method lamer \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-covid.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-covid-test run.txt Run id 26c47264746a1f10 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-news \ --method lamer \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-news.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-news-test run.txt Run id c990d296f840b6a0 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.dlhard \ --method lamer \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ /mnt/data/son/Thesis/t5/data/dlhard/neutral_queries.tsv run.txt Run id bd50ffd2e8e0f2a6 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2019 \ --method lamer \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl19-passage run.txt Run id 4813531aa1f83ce8 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2020 \ --method lamer \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl20-passage run.txt Run id 5f5130519e341b05 · open full run detail →
	mugi	Qwen2.5-72B-Instruct	0.3868	—	0.4103	0.5296	0.2435	—	0.7203	—	0.6927	0.1694	0.5009	0.5921	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	0.3609	0.8122	0.6911	0.9055	0.6268	0.9015
methodmugi llmQwen2.5-72B-Instruct retrieverBM25 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-arguana \ --method mugi \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-arguana.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 \ beir-v1.0.0-arguana-test run.txt Run id 6444a5e04bcb9013 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-dbpedia-entity \ --method mugi \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-dbpedia-entity.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-dbpedia-entity-test run.txt Run id 898543f1681a8169 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-fiqa \ --method mugi \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-fiqa.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 \ beir-v1.0.0-fiqa-test run.txt Run id 831cb39c41716188 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-scifact \ --method mugi \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-scifact.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 \ beir-v1.0.0-scifact-test run.txt Run id fb35e4c85286196d · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-covid \ --method mugi \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-covid.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-covid-test run.txt Run id 74ad89762275ca4e · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-news \ --method mugi \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-news.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-news-test run.txt Run id 20e68a265b0a0f15 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.dlhard \ --method mugi \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ /mnt/data/son/Thesis/t5/data/dlhard/neutral_queries.tsv run.txt Run id 74b697f39b901162 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2019 \ --method mugi \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl19-passage run.txt Run id b8d5bfc95f0c4b50 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2020 \ --method mugi \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl20-passage run.txt Run id 2c11d2c0e20cc0cb · open full run detail →
	mugi	Qwen2.5-7B-Instruct	0.3926	0.9381	0.4006	0.5114	0.2368	0.5652	0.7063	0.9627	0.6771	0.1628	0.4436	0.5767	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	0.3173	0.7707	0.6394	0.8732	0.6069	0.8882
methodmugi llmQwen2.5-7B-Instruct retrieverBM25 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-arguana \ --method mugi \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-arguana.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-arguana-test run.txt Run id 546ff3396d14cb08 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-dbpedia-entity \ --method mugi \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-dbpedia-entity.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-dbpedia-entity-test run.txt Run id 08d0f86de18246a2 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-fiqa \ --method mugi \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-fiqa.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-fiqa-test run.txt Run id 687e67dc791532ef · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-scifact \ --method mugi \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-scifact.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-scifact-test run.txt Run id 357679b380ca5c0f · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-covid \ --method mugi \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-covid.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-covid-test run.txt Run id 31d81c8575bfaaad · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-news \ --method mugi \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-news.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-news-test run.txt Run id 88d0e4a8540d28d0 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.dlhard \ --method mugi \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ /mnt/data/son/Thesis/t5/data/dlhard/neutral_queries.tsv run.txt Run id 646e8a471d7c7a31 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2019 \ --method mugi \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl19-passage run.txt Run id 0bd45569e0452bd6 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2020 \ --method mugi \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl20-passage run.txt Run id ed52ae7274db797c · open full run detail →
	mugi	gpt-4.1	0.3758	0.9331	0.4099	0.5309	0.2641	0.6000	0.7345	0.9660	0.7137	0.1739	0.5156	0.6075	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	0.3651	0.8216	0.6952	0.9005	0.6578	0.8996
methodmugi llmgpt-4.1 retrieverBM25 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-arguana \ --method mugi \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-arguana.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-arguana-test run.txt Run id b74faca3501fd4b0 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-dbpedia-entity \ --method mugi \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-dbpedia-entity.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-dbpedia-entity-test run.txt Run id a3f95b47cce80d6a · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-fiqa \ --method mugi \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-fiqa.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-fiqa-test run.txt Run id 18843a12545a6179 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-scifact \ --method mugi \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-scifact.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-scifact-test run.txt Run id 2665699a986b72c9 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-covid \ --method mugi \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-covid.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-covid-test run.txt Run id bdaf765013c6dc4b · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-news \ --method mugi \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-news.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-news-test run.txt Run id 2baa9c302fcda507 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.dlhard \ --method mugi \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ /mnt/data/son/Thesis/t5/data/dlhard/neutral_queries.tsv run.txt Run id 6f28d412e9569bdf · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2019 \ --method mugi \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl19-passage run.txt Run id 33511f71fb738c32 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2020 \ --method mugi \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl20-passage run.txt Run id ee7db32fd7fd3657 · open full run detail →
	mugi	gpt-4.1-nano	0.3831	0.9317	0.4085	0.5161	0.2517	0.5802	0.7318	0.9627	0.7062	0.1713	0.4707	0.5873	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	0.3423	0.7924	0.6835	0.8915	0.6473	0.9017
methodmugi llmgpt-4.1-nano retrieverBM25 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-arguana \ --method mugi \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-arguana.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-arguana-test run.txt Run id 358094095831f1c0 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-dbpedia-entity \ --method mugi \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-dbpedia-entity.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-dbpedia-entity-test run.txt Run id 06549906899b1593 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-fiqa \ --method mugi \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-fiqa.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-fiqa-test run.txt Run id be4876619f2ae349 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-scifact \ --method mugi \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-scifact.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-scifact-test run.txt Run id 3c130f631cbf4f91 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-covid \ --method mugi \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-covid.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-covid-test run.txt Run id 8fe4f49c828ea9aa · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-news \ --method mugi \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-news.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-news-test run.txt Run id 8e2a04ccecab8874 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.dlhard \ --method mugi \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ /mnt/data/son/Thesis/t5/data/dlhard/neutral_queries.tsv run.txt Run id 242989f63e84fe11 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2019 \ --method mugi \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl19-passage run.txt Run id f43e958c28e0e5af · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2020 \ --method mugi \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl20-passage run.txt Run id 89df7427128a5a65 · open full run detail →
	qa_expand	Qwen2.5-72B-Instruct	0.3995	—	0.3744	0.4709	0.2484	—	0.7015	—	0.6809	0.1600	0.4474	0.5517	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	0.3215	0.7876	0.6109	0.8396	0.6152	0.8727
methodqa_expand llmQwen2.5-72B-Instruct retrieverBM25 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-arguana \ --method qa_expand \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-arguana.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 \ beir-v1.0.0-arguana-test run.txt Run id 596c110a56d70dfe · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-dbpedia-entity \ --method qa_expand \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-dbpedia-entity.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-dbpedia-entity-test run.txt Run id 66a97127eca1d555 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-fiqa \ --method qa_expand \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-fiqa.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 \ beir-v1.0.0-fiqa-test run.txt Run id 96c937c633ca0517 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-scifact \ --method qa_expand \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-scifact.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 \ beir-v1.0.0-scifact-test run.txt Run id b21dd96bd1694da4 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-covid \ --method qa_expand \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-covid.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-covid-test run.txt Run id 107505689e2b41f0 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-news \ --method qa_expand \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-news.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-news-test run.txt Run id 33c770ec0c64ff7b · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.dlhard \ --method qa_expand \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ /mnt/data/son/Thesis/t5/data/dlhard/neutral_queries.tsv run.txt Run id 2157cb85743005b6 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2019 \ --method qa_expand \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl19-passage run.txt Run id 7ac8cd9fc5333fcc · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2020 \ --method qa_expand \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl20-passage run.txt Run id 1e81de4a38d3f0dd · open full run detail →
	qa_expand	Qwen2.5-7B-Instruct	0.3940	0.9324	0.3338	0.4669	0.2234	0.5488	0.6857	0.9347	0.6729	0.1569	0.4340	0.5419	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	0.2892	0.7746	0.5553	0.7976	0.5654	0.8454
methodqa_expand llmQwen2.5-7B-Instruct retrieverBM25 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-arguana \ --method qa_expand \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-arguana.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-arguana-test run.txt Run id 0b1063e73f0d4f40 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-dbpedia-entity \ --method qa_expand \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-dbpedia-entity.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-dbpedia-entity-test run.txt Run id 1ed19024d51ac455 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-fiqa \ --method qa_expand \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-fiqa.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-fiqa-test run.txt Run id 1d90675189dc6500 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-scifact \ --method qa_expand \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-scifact.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-scifact-test run.txt Run id 2442e15fb0f2b05b · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-covid \ --method qa_expand \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-covid.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-covid-test run.txt Run id ea0649fcdfbad201 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-news \ --method qa_expand \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-news.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-news-test run.txt Run id e5700ba0f20ac0d3 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.dlhard \ --method qa_expand \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ /mnt/data/son/Thesis/t5/data/dlhard/neutral_queries.tsv run.txt Run id e9bc830a47e74db3 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2019 \ --method qa_expand \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl19-passage run.txt Run id ffb3f7122f3c8b47 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2020 \ --method qa_expand \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl20-passage run.txt Run id 13736e30246456de · open full run detail →
	qa_expand	gpt-4.1	0.3970	0.9324	0.3699	0.4890	0.2643	0.5814	0.7063	0.9403	0.7065	0.1620	0.4502	0.5608	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	0.3018	0.7570	0.6832	0.8495	0.6418	0.8787
methodqa_expand llmgpt-4.1 retrieverBM25 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-arguana \ --method qa_expand \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-arguana.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-arguana-test run.txt Run id 9b0ab95f82cea1f3 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-dbpedia-entity \ --method qa_expand \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-dbpedia-entity.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-dbpedia-entity-test run.txt Run id d493b98f57ef2733 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-fiqa \ --method qa_expand \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-fiqa.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-fiqa-test run.txt Run id 03710d063184324a · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-scifact \ --method qa_expand \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-scifact.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-scifact-test run.txt Run id 386a7242a957e139 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-covid \ --method qa_expand \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-covid.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-covid-test run.txt Run id 6de5557d87e4b4ed · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-news \ --method qa_expand \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-news.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-news-test run.txt Run id 0e53f287d05ca6e1 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.dlhard \ --method qa_expand \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ /mnt/data/son/Thesis/t5/data/dlhard/neutral_queries.tsv run.txt Run id 7f12baf7cb0f69b7 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2019 \ --method qa_expand \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl19-passage run.txt Run id e67ec513ea055429 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2020 \ --method qa_expand \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl20-passage run.txt Run id 300a1ea4d70fb95f · open full run detail →
	qa_expand	gpt-4.1-nano	0.4021	0.9367	0.3680	0.4808	0.2509	0.5744	0.7059	0.9430	0.6885	0.1583	0.4326	0.5487	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	0.3469	0.7480	0.5819	0.8385	0.6026	0.8649
methodqa_expand llmgpt-4.1-nano retrieverBM25 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-arguana \ --method qa_expand \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-arguana.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-arguana-test run.txt Run id 1a833fc972988aa9 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-dbpedia-entity \ --method qa_expand \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-dbpedia-entity.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-dbpedia-entity-test run.txt Run id 9c31ae911f3ac93f · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-fiqa \ --method qa_expand \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-fiqa.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-fiqa-test run.txt Run id 4c2fff0ca759a5b4 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-scifact \ --method qa_expand \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-scifact.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-scifact-test run.txt Run id 71bd093e88d1661d · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-covid \ --method qa_expand \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-covid.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-covid-test run.txt Run id fac4b7355a15d357 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-news \ --method qa_expand \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-news.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-news-test run.txt Run id 5e2d2c9781d0eb64 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.dlhard \ --method qa_expand \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ /mnt/data/son/Thesis/t5/data/dlhard/neutral_queries.tsv run.txt Run id 5e03acfddafb7f3a · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2019 \ --method qa_expand \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl19-passage run.txt Run id 3e8b7438d8bcac2a · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2020 \ --method qa_expand \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl20-passage run.txt Run id cc360a2a4d13cbe4 · open full run detail →
	Q2D (ZS)	Qwen2.5-72B-Instruct	0.3995	—	0.4034	0.5107	0.2540	—	0.7172	—	0.6973	0.1672	0.4675	0.5557	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	0.3506	0.8002	0.6557	0.8807	0.6207	0.8801
methodQ2D (ZS) llmQwen2.5-72B-Instruct retrieverBM25 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-arguana \ --method query2doc \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train","mode":"zs"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-arguana.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 \ beir-v1.0.0-arguana-test run.txt Run id 8619dbecc084fc26 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-dbpedia-entity \ --method query2doc \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train","mode":"zs"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-dbpedia-entity.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-dbpedia-entity-test run.txt Run id 42a0b43076706ad7 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-fiqa \ --method query2doc \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train","mode":"zs"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-fiqa.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 \ beir-v1.0.0-fiqa-test run.txt Run id acdc3d0f705b0626 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-scifact \ --method query2doc \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train","mode":"zs"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-scifact.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 \ beir-v1.0.0-scifact-test run.txt Run id 6245f4f011f17ead · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-covid \ --method query2doc \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train","mode":"zs"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-covid.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-covid-test run.txt Run id 78f54a86913e8247 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-news \ --method query2doc \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train","mode":"zs"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-news.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-news-test run.txt Run id d5ce0328dc65a110 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.dlhard \ --method query2doc \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train","mode":"zs"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ /mnt/data/son/Thesis/t5/data/dlhard/neutral_queries.tsv run.txt Run id 7257e4c7b7399f3a · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2019 \ --method query2doc \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train","mode":"zs"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl19-passage run.txt Run id de9e52ec1241209f · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2020 \ --method query2doc \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train","mode":"zs"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl20-passage run.txt Run id 0a142166226d768d · open full run detail →
	Q2D (COT)	Qwen2.5-72B-Instruct	0.4060	—	0.3787	0.4778	0.2453	—	0.7077	—	0.6785	0.1590	0.4172	0.5578	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	0.3075	0.7526	0.6378	0.8508	0.5651	0.8549
methodQ2D (COT) llmQwen2.5-72B-Instruct retrieverBM25 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-arguana \ --method query2doc \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"cot","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-arguana.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 \ beir-v1.0.0-arguana-test run.txt Run id 85e17bdc073973ce · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-dbpedia-entity \ --method query2doc \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"cot","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-dbpedia-entity.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-dbpedia-entity-test run.txt Run id ace9ce73f96f3895 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-fiqa \ --method query2doc \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"cot","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-fiqa.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 \ beir-v1.0.0-fiqa-test run.txt Run id 3357fe0963c52576 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-scifact \ --method query2doc \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"cot","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-scifact.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 \ beir-v1.0.0-scifact-test run.txt Run id fd412b5ac4de8ca3 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-covid \ --method query2doc \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"cot","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-covid.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-covid-test run.txt Run id 49d3711fcae40721 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-news \ --method query2doc \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"cot","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-news.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-news-test run.txt Run id d914a0a95d7b5494 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.dlhard \ --method query2doc \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"cot","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ /mnt/data/son/Thesis/t5/data/dlhard/neutral_queries.tsv run.txt Run id 2f716974eaeb6aab · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2019 \ --method query2doc \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"cot","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl19-passage run.txt Run id 8d6339120c7a33ff · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2020 \ --method query2doc \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"cot","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl20-passage run.txt Run id 445f739af46bde73 · open full run detail →
	Q2D (FS)	Qwen2.5-72B-Instruct	0.3991	—	0.3904	0.4993	0.2509	—	0.7163	—	0.7078	0.1673	0.4807	0.6048	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	0.3467	0.8020	0.6875	0.8959	0.6264	0.8907
methodQ2D (FS) llmQwen2.5-72B-Instruct retrieverBM25 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-arguana \ --method query2doc \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"fs","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-arguana.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 \ beir-v1.0.0-arguana-test run.txt Run id a52cee8a07f43fc7 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-dbpedia-entity \ --method query2doc \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"fs","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-dbpedia-entity.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-dbpedia-entity-test run.txt Run id 26e4b3a7f993e212 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-fiqa \ --method query2doc \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"fs","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-fiqa.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 \ beir-v1.0.0-fiqa-test run.txt Run id b8404ff066b9fe20 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-scifact \ --method query2doc \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"fs","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-scifact.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 \ beir-v1.0.0-scifact-test run.txt Run id f82daa013c693bfe · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-covid \ --method query2doc \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"fs","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-covid.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-covid-test run.txt Run id b57adb12adaa79d2 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-news \ --method query2doc \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"fs","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-news.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-news-test run.txt Run id c9cdc67d7569d8b2 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.dlhard \ --method query2doc \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"fs","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ /mnt/data/son/Thesis/t5/data/dlhard/neutral_queries.tsv run.txt Run id ce90fad5adaa8336 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2019 \ --method query2doc \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"fs","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl19-passage run.txt Run id 7846f4e4f7cbdf8e · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2020 \ --method query2doc \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"fs","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl20-passage run.txt Run id 8f3dba10175f7a3a · open full run detail →
	Q2D (COT)	Qwen2.5-7B-Instruct	0.4011	0.9360	0.3669	0.4809	0.2405	0.5544	0.7096	0.9427	0.6997	0.1620	0.4349	0.5616	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	0.3044	0.7815	0.6074	0.8585	0.5802	0.8684
methodQ2D (COT) llmQwen2.5-7B-Instruct retrieverBM25 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-arguana \ --method query2doc \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"cot","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-arguana.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-arguana-test run.txt Run id 1d28b019480c4407 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-dbpedia-entity \ --method query2doc \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"cot","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-dbpedia-entity.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-dbpedia-entity-test run.txt Run id 4a6cb049795632d3 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-fiqa \ --method query2doc \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"cot","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-fiqa.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-fiqa-test run.txt Run id 73ed0aba995f4866 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-scifact \ --method query2doc \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"cot","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-scifact.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-scifact-test run.txt Run id 6301f4ca76c01f2d · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-covid \ --method query2doc \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"cot","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-covid.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-covid-test run.txt Run id fb62aa352bc15877 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-news \ --method query2doc \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"cot","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-news.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-news-test run.txt Run id f3f93eb272b13660 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.dlhard \ --method query2doc \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"cot","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ /mnt/data/son/Thesis/t5/data/dlhard/neutral_queries.tsv run.txt Run id 67d4fcaa1675df48 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2019 \ --method query2doc \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"cot","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl19-passage run.txt Run id 73b4aaf48606190b · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2020 \ --method query2doc \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"cot","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl20-passage run.txt Run id 62c9507b2ac22c16 · open full run detail →
	Q2D (FS)	Qwen2.5-7B-Instruct	0.3984	0.9353	0.3859	0.4831	0.2430	0.5533	0.7149	0.9443	0.7423	0.1668	0.4778	0.5842	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	0.3141	0.7724	0.5884	0.8605	0.5428	0.8691
methodQ2D (FS) llmQwen2.5-7B-Instruct retrieverBM25 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-arguana \ --method query2doc \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"fs","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-arguana.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-arguana-test run.txt Run id 594930d110df8731 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-dbpedia-entity \ --method query2doc \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"fs","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-dbpedia-entity.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-dbpedia-entity-test run.txt Run id 44515c9e869aaff4 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-fiqa \ --method query2doc \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"fs","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-fiqa.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-fiqa-test run.txt Run id 71812da24a9de0e5 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-scifact \ --method query2doc \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"fs","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-scifact.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-scifact-test run.txt Run id d460875ca7114d6c · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-covid \ --method query2doc \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"fs","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-covid.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-covid-test run.txt Run id 78eec3302fce551a · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-news \ --method query2doc \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"fs","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-news.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-news-test run.txt Run id 72e49bd1ea5571d2 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.dlhard \ --method query2doc \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"fs","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ /mnt/data/son/Thesis/t5/data/dlhard/neutral_queries.tsv run.txt Run id 4549e09aba8d1d38 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2019 \ --method query2doc \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"fs","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl19-passage run.txt Run id df47ee08000db77b · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2020 \ --method query2doc \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"fs","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl20-passage run.txt Run id 502160d92b6d3bbd · open full run detail →
	Q2D (ZS)	Qwen2.5-7B-Instruct	0.4007	0.9353	0.3836	0.5047	0.2460	0.5597	0.7042	0.9443	0.7071	0.1628	0.4507	0.5561	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	0.3352	0.7763	0.6014	0.8467	0.5685	0.8647
methodQ2D (ZS) llmQwen2.5-7B-Instruct retrieverBM25 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-arguana \ --method query2doc \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train","mode":"zs"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-arguana.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-arguana-test run.txt Run id 62e52fd01525fb50 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-dbpedia-entity \ --method query2doc \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train","mode":"zs"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-dbpedia-entity.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-dbpedia-entity-test run.txt Run id 22d170e3fbbc7a61 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-fiqa \ --method query2doc \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train","mode":"zs"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-fiqa.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-fiqa-test run.txt Run id 2ebb11584acb74e3 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-scifact \ --method query2doc \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train","mode":"zs"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-scifact.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-scifact-test run.txt Run id 71bb53177909776f · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-covid \ --method query2doc \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train","mode":"zs"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-covid.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-covid-test run.txt Run id facc5bc340b19269 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-news \ --method query2doc \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train","mode":"zs"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-news.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-news-test run.txt Run id 5f13bb51f6d902d5 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.dlhard \ --method query2doc \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train","mode":"zs"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ /mnt/data/son/Thesis/t5/data/dlhard/neutral_queries.tsv run.txt Run id 03f7128ac3b310e8 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2019 \ --method query2doc \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"zs"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl19-passage run.txt Run id e923c68752d5194e · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2020 \ --method query2doc \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train","mode":"zs"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl20-passage run.txt Run id 10225b870ee90958 · open full run detail →
	Q2D (ZS)	gpt-4.1	0.3970	0.9324	0.4062	0.5051	0.2599	0.6002	0.7203	0.9477	0.7430	0.1704	0.4980	0.5858	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	0.3502	0.7811	0.6873	0.8924	0.6625	0.8942
methodQ2D (ZS) llmgpt-4.1 retrieverBM25 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-arguana \ --method query2doc \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train","mode":"zs"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-arguana.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-arguana-test run.txt Run id d204ccdf69c4e24d · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-dbpedia-entity \ --method query2doc \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train","mode":"zs"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-dbpedia-entity.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-dbpedia-entity-test run.txt Run id de7f901445af8902 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-fiqa \ --method query2doc \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train","mode":"zs"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-fiqa.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-fiqa-test run.txt Run id 62979f46f25929ac · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-scifact \ --method query2doc \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train","mode":"zs"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-scifact.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-scifact-test run.txt Run id ed7c32bfd736261d · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-covid \ --method query2doc \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train","mode":"zs"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-covid.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-covid-test run.txt Run id 77259373e25a7a52 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-news \ --method query2doc \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train","mode":"zs"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-news.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-news-test run.txt Run id 8ac866d9b5e4ee65 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.dlhard \ --method query2doc \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train","mode":"zs"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ /mnt/data/son/Thesis/t5/data/dlhard/neutral_queries.tsv run.txt Run id 75a33d8c216d3b0a · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2019 \ --method query2doc \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train","mode":"zs"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl19-passage run.txt Run id 196e027939a4324f · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2020 \ --method query2doc \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train","mode":"zs"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl20-passage run.txt Run id e79f10ad54392ac3 · open full run detail →
	Q2D (COT)	gpt-4.1	0.4028	0.9374	0.3934	0.4775	0.2578	0.5843	0.7135	0.9510	0.7277	0.1696	0.4656	0.5829	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	0.3291	0.7737	0.6528	0.8777	0.6239	0.8781
methodQ2D (COT) llmgpt-4.1 retrieverBM25 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-arguana \ --method query2doc \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"cot","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-arguana.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-arguana-test run.txt Run id 3dc298044f91170e · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-dbpedia-entity \ --method query2doc \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"cot","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-dbpedia-entity.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-dbpedia-entity-test run.txt Run id 6de7438014621dae · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-fiqa \ --method query2doc \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"cot","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-fiqa.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-fiqa-test run.txt Run id 66938a0060985598 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-scifact \ --method query2doc \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"cot","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-scifact.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-scifact-test run.txt Run id 9d4475bc0338e1a9 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-covid \ --method query2doc \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"cot","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-covid.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-covid-test run.txt Run id 7eba1b0cd9c3aeac · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-news \ --method query2doc \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"cot","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-news.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-news-test run.txt Run id 5f3b6de0773416c1 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.dlhard \ --method query2doc \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"cot","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ /mnt/data/son/Thesis/t5/data/dlhard/neutral_queries.tsv run.txt Run id 209ab08dd85710d7 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2019 \ --method query2doc \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"cot","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl19-passage run.txt Run id ee4a161964a18e42 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2020 \ --method query2doc \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"cot","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl20-passage run.txt Run id e76380613860506a · open full run detail →
	Q2D (FS)	gpt-4.1	0.4012	0.9410	0.4010	0.5083	0.2684	0.5993	0.7123	0.9493	0.7081	0.1639	0.4801	0.5842	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	0.3562	0.8042	0.6904	0.8861	0.6746	0.8984
methodQ2D (FS) llmgpt-4.1 retrieverBM25 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-arguana \ --method query2doc \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"fs","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-arguana.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-arguana-test run.txt Run id 855dea1f38920b07 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-dbpedia-entity \ --method query2doc \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"fs","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-dbpedia-entity.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-dbpedia-entity-test run.txt Run id 34623e48f90c3cc1 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-fiqa \ --method query2doc \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"fs","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-fiqa.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-fiqa-test run.txt Run id 6bfad70532b504da · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-scifact \ --method query2doc \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"fs","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-scifact.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-scifact-test run.txt Run id cc81773cafb3e49b · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-covid \ --method query2doc \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"fs","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-covid.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-covid-test run.txt Run id cb9b33c3da55c047 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-news \ --method query2doc \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"fs","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-news.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-news-test run.txt Run id 1cc44d38cba745c8 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.dlhard \ --method query2doc \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"fs","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ /mnt/data/son/Thesis/t5/data/dlhard/neutral_queries.tsv run.txt Run id d3a0e5118a282df0 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2019 \ --method query2doc \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"fs","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl19-passage run.txt Run id c995d4ba0c450885 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2020 \ --method query2doc \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"fs","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl20-passage run.txt Run id 46298ea9c2569a93 · open full run detail →
	Q2D (COT)	gpt-4.1-nano	0.4011	0.9360	0.3921	0.5132	0.2557	0.5758	0.7273	0.9560	0.7503	0.1744	0.4601	0.5728	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	0.3320	0.7655	0.6254	0.8621	0.6092	0.8846
methodQ2D (COT) llmgpt-4.1-nano retrieverBM25 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-arguana \ --method query2doc \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"cot","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-arguana.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-arguana-test run.txt Run id dff54a27d7cedded · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-dbpedia-entity \ --method query2doc \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"cot","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-dbpedia-entity.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-dbpedia-entity-test run.txt Run id bc3f5b2a9398d8be · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-fiqa \ --method query2doc \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"cot","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-fiqa.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-fiqa-test run.txt Run id 1376d501eb497974 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-scifact \ --method query2doc \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"cot","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-scifact.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-scifact-test run.txt Run id 4aa112baf1b01f83 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-covid \ --method query2doc \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"cot","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-covid.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-covid-test run.txt Run id fceeb2e49e8d7c97 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-news \ --method query2doc \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"cot","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-news.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-news-test run.txt Run id 8a7882d9005a0389 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.dlhard \ --method query2doc \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"cot","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ /mnt/data/son/Thesis/t5/data/dlhard/neutral_queries.tsv run.txt Run id caf314781f9fe17b · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2019 \ --method query2doc \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"cot","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl19-passage run.txt Run id 4eb07554571bf4aa · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2020 \ --method query2doc \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"cot","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl20-passage run.txt Run id e4722d522fbe0f37 · open full run detail →
	Q2D (FS)	gpt-4.1-nano	0.3965	0.9324	0.3720	0.4873	0.2531	0.5833	0.7053	0.9410	0.6827	0.1634	0.4442	0.5398	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	0.3358	0.7627	0.6643	0.8527	0.6227	0.8848
methodQ2D (FS) llmgpt-4.1-nano retrieverBM25 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-arguana \ --method query2doc \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"fs","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-arguana.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-arguana-test run.txt Run id 39a00cbcddc345d8 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-dbpedia-entity \ --method query2doc \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"fs","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-dbpedia-entity.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-dbpedia-entity-test run.txt Run id bf0024f85cb42407 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-fiqa \ --method query2doc \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"fs","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-fiqa.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-fiqa-test run.txt Run id f7d84e961ff5f12f · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-scifact \ --method query2doc \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"fs","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-scifact.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-scifact-test run.txt Run id 95bd7ea7d41c9761 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-covid \ --method query2doc \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"fs","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-covid.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-covid-test run.txt Run id 6fd7188c2ec94cec · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-news \ --method query2doc \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"fs","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-news.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-news-test run.txt Run id 6503b696a29566b0 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.dlhard \ --method query2doc \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"fs","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ /mnt/data/son/Thesis/t5/data/dlhard/neutral_queries.tsv run.txt Run id c832e5deec3b5b50 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2019 \ --method query2doc \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"fs","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl19-passage run.txt Run id 47f9b50aa4ac8e38 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2020 \ --method query2doc \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"fs","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl20-passage run.txt Run id d1c162f3189b28c9 · open full run detail →
	Q2D (ZS)	gpt-4.1-nano	0.3980	0.9374	0.3968	0.4980	0.2548	0.5899	0.7170	0.9403	0.6967	0.1656	0.4685	0.5564	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	0.3368	0.7832	0.6779	0.8862	0.6268	0.8869
methodQ2D (ZS) llmgpt-4.1-nano retrieverBM25 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-arguana \ --method query2doc \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train","mode":"zs"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-arguana.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-arguana-test run.txt Run id 5b4589eaf5d5958a · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-dbpedia-entity \ --method query2doc \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train","mode":"zs"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-dbpedia-entity.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-dbpedia-entity-test run.txt Run id 076923834bf2f177 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-fiqa \ --method query2doc \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train","mode":"zs"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-fiqa.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-fiqa-test run.txt Run id 1915b96aa0c6de16 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-scifact \ --method query2doc \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train","mode":"zs"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-scifact.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-scifact-test run.txt Run id 670d751a8dfb1ae0 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-covid \ --method query2doc \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train","mode":"zs"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-covid.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-covid-test run.txt Run id 451847c083f4e7d3 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-news \ --method query2doc \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train","mode":"zs"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-news.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-news-test run.txt Run id 0a6dffe3d6683d31 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.dlhard \ --method query2doc \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train","mode":"zs"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ /mnt/data/son/Thesis/t5/data/dlhard/neutral_queries.tsv run.txt Run id 6dbe29f0381ea74a · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2019 \ --method query2doc \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train","mode":"zs"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl19-passage run.txt Run id 50f98f9827c168fa · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2020 \ --method query2doc \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train","mode":"zs"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl20-passage run.txt Run id 41cb8703d305ec7a · open full run detail →
	query2e	Qwen2.5-72B-Instruct	0.4066	—	0.3578	0.4641	0.2518	—	0.6969	—	0.6942	0.1611	0.4484	0.5647	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	0.3148	0.7605	0.5845	0.8501	0.5546	0.8609
methodquery2e llmQwen2.5-72B-Instruct retrieverBM25 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-arguana \ --method query2e \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-arguana.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 \ beir-v1.0.0-arguana-test run.txt Run id 40f110d0a40bc926 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-dbpedia-entity \ --method query2e \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-dbpedia-entity.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-dbpedia-entity-test run.txt Run id 835fd60092d69d40 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-fiqa \ --method query2e \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-fiqa.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 \ beir-v1.0.0-fiqa-test run.txt Run id f74f30707b9b167c · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-scifact \ --method query2e \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-scifact.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 \ beir-v1.0.0-scifact-test run.txt Run id c9364b60bcba9cc6 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-covid \ --method query2e \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-covid.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-covid-test run.txt Run id d522590b4b14d2f8 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-news \ --method query2e \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-news.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-news-test run.txt Run id ffa251db10b65250 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.dlhard \ --method query2e \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ /mnt/data/son/Thesis/t5/data/dlhard/neutral_queries.tsv run.txt Run id 130dd4da2379e09b · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2019 \ --method query2e \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl19-passage run.txt Run id 71fabe1af05dfe6e · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2020 \ --method query2e \ --model Qwen/Qwen2.5-72B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl20-passage run.txt Run id 9ce92bd9a02b250b · open full run detail →
	query2e	Qwen2.5-7B-Instruct	0.4052	0.9403	0.3477	0.4691	0.2453	0.5494	0.6967	0.9520	0.6945	0.1653	0.4503	0.5824	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	0.3101	0.7432	0.5721	0.8431	0.5404	0.8548
methodquery2e llmQwen2.5-7B-Instruct retrieverBM25 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-arguana \ --method query2e \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-arguana.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-arguana-test run.txt Run id af1560c7b48c9a40 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-dbpedia-entity \ --method query2e \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-dbpedia-entity.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-dbpedia-entity-test run.txt Run id 36919c88ea5e5218 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-fiqa \ --method query2e \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-fiqa.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-fiqa-test run.txt Run id 13827910963f743c · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-scifact \ --method query2e \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-scifact.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-scifact-test run.txt Run id 08ca78b716915e59 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-covid \ --method query2e \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-covid.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-covid-test run.txt Run id 7be63943b9134828 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-news \ --method query2e \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-news.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-news-test run.txt Run id 9a103d83631d9cae · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.dlhard \ --method query2e \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ /mnt/data/son/Thesis/t5/data/dlhard/neutral_queries.tsv run.txt Run id efc5a614cfca2157 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2019 \ --method query2e \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"mode":"zs","num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl19-passage run.txt Run id 1e142ccfe450e0ea · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2020 \ --method query2e \ --model Qwen/Qwen2.5-7B-Instruct \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl20-passage run.txt Run id 0a4272e5995a875c · open full run detail →
	query2e	gpt-4.1	0.4062	0.9381	0.3778	0.4772	0.2690	0.5930	0.7089	0.9403	0.7150	0.1772	0.4633	0.5807	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	0.3446	0.7639	0.5935	0.8698	0.5759	0.8594
methodquery2e llmgpt-4.1 retrieverBM25 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-arguana \ --method query2e \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-arguana.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-arguana-test run.txt Run id 2a57117923fd8fb7 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-dbpedia-entity \ --method query2e \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-dbpedia-entity.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-dbpedia-entity-test run.txt Run id 2e4fc8b19b6058f4 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-fiqa \ --method query2e \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-fiqa.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-fiqa-test run.txt Run id 9c912226a2c5bbf6 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-scifact \ --method query2e \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-scifact.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-scifact-test run.txt Run id 87a5b6a51c2d0cd9 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-covid \ --method query2e \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-covid.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-covid-test run.txt Run id 83a104d9072d36aa · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-news \ --method query2e \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-news.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-news-test run.txt Run id 6e63b6a8bd5c7bac · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.dlhard \ --method query2e \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ /mnt/data/son/Thesis/t5/data/dlhard/neutral_queries.tsv run.txt Run id 0fba97775fd0d080 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2019 \ --method query2e \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl19-passage run.txt Run id 7b8fc1dd302a218f · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2020 \ --method query2e \ --model openai/gpt-4.1 \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl20-passage run.txt Run id 29c337ef79c2d1ce · open full run detail →
	query2e	gpt-4.1-nano	0.4060	0.9417	0.3597	0.4696	0.2524	0.5779	0.7016	0.9480	0.7373	0.1765	0.4557	0.5827	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	—	0.3101	0.7665	0.5891	0.8474	0.5475	0.8392
methodquery2e llmgpt-4.1-nano retrieverBM25 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-arguana \ --method query2e \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-arguana.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-arguana-test run.txt Run id afa308143ca6fc36 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-dbpedia-entity \ --method query2e \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-dbpedia-entity.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-dbpedia-entity-test run.txt Run id 7f6313d4c075acc0 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-fiqa \ --method query2e \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-fiqa.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-fiqa-test run.txt Run id 794863ac2716ff10 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-scifact \ --method query2e \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-scifact.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-scifact-test run.txt Run id 5b80ece5f5b6d217 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-covid \ --method query2e \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-covid.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-covid-test run.txt Run id e9657ef06091d19d · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset beir-v1.0.0-trec-news \ --method query2e \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index beir-v1.0.0-trec-news.flat \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@100 python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.100 \ beir-v1.0.0-trec-news-test run.txt Run id 769a2fbb87682377 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.dlhard \ --method query2e \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ /mnt/data/son/Thesis/t5/data/dlhard/neutral_queries.tsv run.txt Run id 881251d288163f86 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2019 \ --method query2e \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl19-passage run.txt Run id 173d4249c65da6f0 · open full run detail → 1 reformulate querygym → reformulated_queries.tsv python examples/querygym_pyserini/pipeline.py \ --dataset msmarco-v1-passage.trecdl2020 \ --method query2e \ --model openai/gpt-4.1-nano \ --steps reformulate \ --temperature 1 \ --max-tokens 128 \ --method-params '{"num_examples":4,"train_split":"train"}' \ --output-dir outputs/reproduce 2 retrieve pyserini · BM25 (lexical) python -m pyserini.search.lucene \ --threads 16 --batch-size 128 \ --index msmarco-v1-passage \ --topics outputs/reproduce/queries/reformulated_queries.tsv \ --bm25 --k1 0.9 --b 0.4 \ --output run.txt \ --hits 1000 3 evaluate trec_eval · nDCG@10 + R@1k python -m pyserini.eval.trec_eval -c -m ndcg.cut.10 -m recall.1000 \ dl20-passage run.txt Run id 4dba6fc69920dec7 · open full run detail →