{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/dense-passage-retrieval-for-open-domain","title":"Dense Passage Retrieval for Open-Domain Question Answering","arxiv_id":"2004.04906","date":"2020-04-10","proceeding":"EMNLP 2020 11","authors":["Vladimir Karpukhin","Barlas Oğuz","Sewon Min","Patrick Lewis","Ledell Wu","Sergey Edunov","Danqi Chen","Wen-tau Yih"],"abstract":"Open-domain question answering relies on efficient passage retrieval to select candidate contexts, where traditional sparse vector space models, such as TF-IDF or BM25, are the de facto method. In this work, we show that retrieval can be practically implemented using dense representations alone, where embeddings are learned from a small number of questions and passages by a simple dual-encoder framework. When evaluated on a wide range of open-domain QA datasets, our dense retriever outperforms a strong Lucene-BM25 system largely by 9%-19% absolute in terms of top-20 passage retrieval accuracy, and helps our end-to-end QA system establish new state-of-the-art on multiple open-domain QA benchmarks.","url_abs":"https://arxiv.org/abs/2004.04906v3","url_pdf":"https://arxiv.org/pdf/2004.04906v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"dense-passage-retrieval-for-open-domain","repo_url":"https://github.com/facebookresearch/DPR","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"dense-passage-retrieval-for-open-domain","repo_url":"https://github.com/AhmedHussKhalifa/Dense_Passage_Retrieval_in_Conversational_Search","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"dense-passage-retrieval-for-open-domain","repo_url":"https://github.com/AkariAsai/XORQA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"dense-passage-retrieval-for-open-domain","repo_url":"https://github.com/Ankur3107/dpr-tf","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"dense-passage-retrieval-for-open-domain","repo_url":"https://github.com/DevSinghSachan/unsupervised-passage-reranking","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"dense-passage-retrieval-for-open-domain","repo_url":"https://github.com/Hannibal046/nanoDPR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"dense-passage-retrieval-for-open-domain","repo_url":"https://github.com/alexlimh/DPR_MUF","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"dense-passage-retrieval-for-open-domain","repo_url":"https://github.com/amzn/refuel-open-domain-qa","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"dense-passage-retrieval-for-open-domain","repo_url":"https://github.com/deepset-ai/haystack","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"dense-passage-retrieval-for-open-domain","repo_url":"https://github.com/efficientqa/retrieval-based-baselines","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"dense-passage-retrieval-for-open-domain","repo_url":"https://github.com/hongyuntw/DPR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"dense-passage-retrieval-for-open-domain","repo_url":"https://github.com/hongyuntw/DPR_BESS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"dense-passage-retrieval-for-open-domain","repo_url":"https://github.com/huggingface/transformers","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"dense-passage-retrieval-for-open-domain","repo_url":"https://github.com/junnyu/dpr_paddle","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"paddle","reach":{"status":"ok"}},{"paper_slug":"dense-passage-retrieval-for-open-domain","repo_url":"https://github.com/luyug/GC-DPR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"dense-passage-retrieval-for-open-domain","repo_url":"https://github.com/nidhikamal-emb/DPR_repo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"dense-passage-retrieval-for-open-domain","repo_url":"https://github.com/openmatch/ance-tele","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"unanswered"}},{"paper_slug":"dense-passage-retrieval-for-open-domain","repo_url":"https://github.com/oriram/spider","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"dense-passage-retrieval-for-open-domain","repo_url":"https://github.com/texttron/tevatron","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"open-domain-question-answering","task_name":"Open-Domain Question Answering"},{"task_slug":"passage-retrieval","task_name":"Passage Retrieval"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/passage-retrieval-on-natural-questions","task":"Passage Retrieval","dataset":"Natural Questions","model":"DPR","rank_in_archive_order":8,"of":10,"metrics":{"Precision@100":"86","Precision@20":"79.4"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-natural-questions","task":"Question Answering","dataset":"Natural Questions","model":"DPR","rank_in_archive_order":23,"of":47,"metrics":{"EM":"41.5"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-naturalqa","task":"Question Answering","dataset":"NaturalQA","model":"DPR","rank_in_archive_order":1,"of":4,"metrics":{"EM":"41.5"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-triviaqa","task":"Question Answering","dataset":"TriviaQA","model":"DPR","rank_in_archive_order":41,"of":56,"metrics":{"EM":"56.8"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-webquestions","task":"Question Answering","dataset":"WebQuestions","model":"DPR","rank_in_archive_order":17,"of":37,"metrics":{"EM":"42.4"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2004.04906","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.04906"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/huggingface/transformers","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/alexlimh/DPR_MUF","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/oriram/spider","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/DevSinghSachan/unsupervised-passage-reranking","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/efficientqa/retrieval-based-baselines","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/openmatch/ance-tele","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Ankur3107/dpr-tf","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hongyuntw/DPR","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/luyug/GC-DPR","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/texttron/tevatron","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/deepset-ai/haystack","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/facebookresearch/DPR","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/AhmedHussKhalifa/Dense_Passage_Retrieval_in_Conversational_Search","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hongyuntw/DPR_BESS","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/junnyu/dpr_paddle","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Hannibal046/nanoDPR","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/AkariAsai/XORQA","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/amzn/refuel-open-domain-qa","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nidhikamal-emb/DPR_repo","reach":null}],"summary":{"ran":9,"ran_draft_wrong":1,"unverified":4},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1},"listed":{"samples":13,"ran":10,"repositories":9}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":9,"samples":[{"code_sha256_prefix":"0c54070c4beb2fe8","entry":"BiEncoder","repo":"hongyuntw/DPR","repo_kind":"listed","path":"dpr/models/biencoder.py","file_url":"https://github.com/hongyuntw/DPR/blob/HEAD/dpr/models/biencoder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"0c54070c4beb2fe8"}},{"code_sha256_prefix":"e07f372e147c2a51","entry":"BiEncoder","repo":"oriram/spider","repo_kind":"listed","path":"dpr/models/biencoder.py","file_url":"https://github.com/oriram/spider/blob/HEAD/dpr/models/biencoder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e07f372e147c2a51"}},{"code_sha256_prefix":"49b5e44493f56195","entry":"BiEncoder","repo":"AkariAsai/XORQA","repo_kind":"listed","path":"baselines/DPR/dpr/models/biencoder.py","file_url":"https://github.com/AkariAsai/XORQA/blob/HEAD/baselines/DPR/dpr/models/biencoder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"49b5e44493f56195"}},{"code_sha256_prefix":"2a7bedc5746a0acb","entry":"BiEncoder","repo":"luyug/GC-DPR","repo_kind":"listed","path":"dpr/models/biencoder.py","file_url":"https://github.com/luyug/GC-DPR/blob/HEAD/dpr/models/biencoder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"2a7bedc5746a0acb"}},{"code_sha256_prefix":"2636897c847a74e7","entry":"BiEncoder","repo":"alexlimh/DPR_MUF","repo_kind":"listed","path":"dpr/models/biencoder.py","file_url":"https://github.com/alexlimh/DPR_MUF/blob/HEAD/dpr/models/biencoder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2636897c847a74e7"}},{"code_sha256_prefix":"f395e69cf2723c98","entry":"BiEncoder","repo":"nidhikamal-emb/DPR_repo","repo_kind":"listed","path":"dpr/models/biencoder.py","file_url":"https://github.com/nidhikamal-emb/DPR_repo/blob/HEAD/dpr/models/biencoder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"f395e69cf2723c98"}},{"code_sha256_prefix":"1ccc1581e033d222","entry":"BiEncoderBatch","repo":"luyug/GC-DPR","repo_kind":"listed","path":"dpr/models/biencoder.py","file_url":"https://github.com/luyug/GC-DPR/blob/HEAD/dpr/models/biencoder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"1ccc1581e033d222"}},{"code_sha256_prefix":"66b0a842536d2529","entry":"DualEncoder","repo":"Hannibal046/nanoDPR","repo_kind":"listed","path":"train_dpr.py","file_url":"https://github.com/Hannibal046/nanoDPR/blob/HEAD/train_dpr.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"66b0a842536d2529"}},{"code_sha256_prefix":"74f56feb6089930e","entry":"MyBiEncoder","repo":"amzn/refuel-open-domain-qa","repo_kind":"listed","path":"models/biencoder.py","file_url":"https://github.com/amzn/refuel-open-domain-qa/blob/HEAD/models/biencoder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"74f56feb6089930e"}},{"code_sha256_prefix":"e34c0cb58f92bbab","entry":"normalize_question","repo":"hongyuntw/DPR","repo_kind":"listed","path":"dpr/models/biencoder.py","file_url":"https://github.com/hongyuntw/DPR/blob/HEAD/dpr/models/biencoder.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"e34c0cb58f92bbab"}},{"code_sha256_prefix":"ce8859f3bf1c3bff","entry":"BiEncoder","repo":"facebookresearch/DPR","repo_kind":"official","path":"dpr/models/biencoder.py","file_url":"https://github.com/facebookresearch/DPR/blob/HEAD/dpr/models/biencoder.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"ce8859f3bf1c3bff"}},{"code_sha256_prefix":"15a8673b02cc06ff","entry":"Tensorizer","repo":"hongyuntw/DPR","repo_kind":"listed","path":"dpr/models/biencoder.py","file_url":"https://github.com/hongyuntw/DPR/blob/HEAD/dpr/models/biencoder.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"15a8673b02cc06ff"}},{"code_sha256_prefix":"62589f451f5aa0bd","entry":"Tensorizer","repo":"oriram/spider","repo_kind":"listed","path":"dpr/models/biencoder.py","file_url":"https://github.com/oriram/spider/blob/HEAD/dpr/models/biencoder.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"62589f451f5aa0bd"}},{"code_sha256_prefix":"6daeb2af140c2153","entry":"cross_replica_concat","repo":"Ankur3107/dpr-tf","repo_kind":"listed","path":"src/dense_passage_retriever.py","file_url":"https://github.com/Ankur3107/dpr-tf/blob/HEAD/src/dense_passage_retriever.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6daeb2af140c2153"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}