Papers › Dense Passage Retrieval for Open-Domain Question Answering

Dense Passage Retrieval for Open-Domain Question Answering

10 Apr 2020EMNLP 2020 11arXiv:2004.04906archive 2025-07-28

Vladimir Karpukhin, Barlas Oğuz, Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, Wen-tau Yih

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.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2004.04906")

Code

Syntology Ran 10 of 14 code samples harvested from 10 repositories linked to this paper; 4 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 9 ran with no contract checked.

By repository: official repository: 1 sample from 1 repository, 0 ran; community (archive-listed): 13 samples from 9 repositories, 10 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

19 repositories listed; official and paper-mentioned ones first.

facebookresearch/DPR officialmentioned in papermentioned on GitHubpytorch report
AkariAsai/XORQA mentioned on GitHubpytorch report
Ankur3107/dpr-tf mentioned on GitHubtfMIT report
Hannibal046/nanoDPR mentioned on GitHubpytorch report
alexlimh/DPR_MUF mentioned on GitHubpytorch report
amzn/refuel-open-domain-qa mentioned on GitHubpytorch report
deepset-ai/haystack mentioned on GitHubpytorchApache-2.0 report
efficientqa/retrieval-based-baselines mentioned on GitHubtfNOASSERTION report
hongyuntw/DPR mentioned on GitHubpytorch report
hongyuntw/DPR_BESS mentioned on GitHubpytorchNOASSERTION report
huggingface/transformers mentioned on GitHubpytorch report
junnyu/dpr_paddle mentioned on GitHubpaddle report
luyug/GC-DPR mentioned on GitHubpytorch report
nidhikamal-emb/DPR_repo mentioned on GitHubpytorch report
openmatch/ance-tele mentioned on GitHubjax report
oriram/spider mentioned on GitHubpytorch report
texttron/tevatron jaxApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

14 samples harvested; 10 ran; 0 honoured the contract we drafted; 4 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
9ran
4unverified

Licence: 9 of the 14 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 10 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

BiEncoder facebookresearch/DPR/dpr/models/biencoder.py official repository unverified licence not identified · pointer only · ce8859f3bf1c3bff · report
BiEncoder hongyuntw/DPR/dpr/models/biencoder.py community (archive-listed) ran · metamorphic tier: deterministic licence not identified · pointer only · 0c54070c4beb2fe8 · report
BiEncoder oriram/spider/dpr/models/biencoder.py community (archive-listed) ran · metamorphic tier: deterministic MIT (permissive) · e07f372e147c2a51 · report
BiEncoder AkariAsai/XORQA/baselines/DPR/dpr/models/biencoder.py community (archive-listed) ran · metamorphic tier: deterministic MIT (permissive) · 49b5e44493f56195 · report
BiEncoder luyug/GC-DPR/dpr/models/biencoder.py community (archive-listed) ran licence not identified · pointer only · 2a7bedc5746a0acb · report
BiEncoder alexlimh/DPR_MUF/dpr/models/biencoder.py community (archive-listed) ran no licence file found · pointer only · 2636897c847a74e7 · report
BiEncoder nidhikamal-emb/DPR_repo/dpr/models/biencoder.py community (archive-listed) ran licence not identified · pointer only · f395e69cf2723c98 · report
BiEncoderBatch luyug/GC-DPR/dpr/models/biencoder.py community (archive-listed) ran licence not identified · pointer only · 1ccc1581e033d222 · report
DualEncoder Hannibal046/nanoDPR/train_dpr.py community (archive-listed) ran · metamorphic tier: deterministic no licence file found · pointer only · 66b0a842536d2529 · report
MyBiEncoder amzn/refuel-open-domain-qa/models/biencoder.py community (archive-listed) ran Apache-2.0 (permissive) · 74f56feb6089930e · report
normalize_question hongyuntw/DPR/dpr/models/biencoder.py community (archive-listed) ran · our draft was wrong fingerprinted licence not identified · pointer only · e34c0cb58f92bbab · report
Tensorizer hongyuntw/DPR/dpr/models/biencoder.py community (archive-listed) unverified licence not identified · pointer only · 15a8673b02cc06ff · report
Tensorizer oriram/spider/dpr/models/biencoder.py community (archive-listed) unverified MIT (permissive) · 62589f451f5aa0bd · report
cross_replica_concat Ankur3107/dpr-tf/src/dense_passage_retriever.py community (archive-listed) unverified MIT (permissive) · 6daeb2af140c2153 · report

Tasks

Open-Domain Question AnsweringPassage RetrievalQuestion AnsweringRetrieval

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Passage Retrieval Natural Questions DPR Precision@100 86 #8 of 10 Archive leaderboard report
Passage Retrieval Natural Questions DPR Precision@20 79.4 #8 of 10 Archive leaderboard report
Question Answering Natural Questions DPR EM 41.5 #23 of 47 Archive leaderboard report
Question Answering NaturalQA DPR EM 41.5 #1 of 4 Archive leaderboard report
Question Answering TriviaQA DPR EM 56.8 #41 of 56 Archive leaderboard report
Question Answering WebQuestions DPR EM 42.4 #17 of 37 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections