Papers › Unsupervised Dense Information Retrieval with Contrastive Learning

Unsupervised Dense Information Retrieval with Contrastive Learning

16 Dec 2021arXiv:2112.09118archive 2025-07-28

Gautier Izacard, Mathilde Caron, Lucas Hosseini, Sebastian Riedel, Piotr Bojanowski, Armand Joulin, Edouard Grave

Recently, information retrieval has seen the emergence of dense retrievers, using neural networks, as an alternative to classical sparse methods based on term-frequency. These models have obtained state-of-the-art results on datasets and tasks where large training sets are available. However, they do not transfer well to new applications with no training data, and are outperformed by unsupervised term-frequency methods such as BM25. In this work, we explore the limits of contrastive learning as a way to train unsupervised dense retrievers and show that it leads to strong performance in various retrieval settings. On the BEIR benchmark our unsupervised model outperforms BM25 on 11 out of 15 datasets for the Recall@100. When used as pre-training before fine-tuning, either on a few thousands in-domain examples or on the large MS MARCO dataset, our contrastive model leads to improvements on the BEIR benchmark. Finally, we evaluate our approach for multi-lingual retrieval, where training data is even scarcer than for English, and show that our approach leads to strong unsupervised performance. Our model also exhibits strong cross-lingual transfer when fine-tuned on supervised English data only and evaluated on low resources language such as Swahili. We show that our unsupervised models can perform cross-lingual retrieval between different scripts, such as retrieving English documents from Arabic queries, which would not be possible with term matching methods.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

No sample from the archive's official repository (facebookresearch/contriever) is linked to this paper; the 5 samples below come from 1 community repository. Syntology harvested code from facebookresearch/contriever for another paper.

facebookresearch/contriever: Syntology's graph links these samples to Back to Basics: Let Conversational Agents Remember with Just Retrieval and Generation (arXiv:2604.11628; that paper's own run record: 16 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 4 honoured, 3 violated, 0 with no contract checked; 9 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method.

Syntology 5 code samples harvested from 1 repository linked to this paper: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 5 samples from 1 repository, 4 ran (4 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

facebookresearch/contriever officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Back to Basics: Let Conversational Agents Remember with Just Retrieval and Generation (arXiv:2604.11628; that paper's own run record: 16 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 4 honoured, 3 violated, 0 with no contract checked; 9 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
DevSinghSachan/unsupervised-passage-reranking mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Improving Passage Retrieval with Zero-Shot Question Generation (arXiv:2204.07496; that paper's own run record: 8 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
nthakur20/income mentioned on GitHubpytorchApache-2.0Syntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified report
soldni/pyterrier_sentence_transformers mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
thakur-nandan/income mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
xfactlab/emnlp2023-damaging-retrieval mentioned on GitHubpytorchSyntology: not harvested 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

5 samples harvested: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

4ran
1unverified

Licence: 1 of the 5 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from nthakur20/income. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

nthakur20/income community (archive-listed) 5 samples, 4 ran (0 instrument-failed) · 1 unverified
PassagePreprocessingFn income/jpq/preprocess.py ran Apache-2.0 (permissive) · 0ffcad8ea0548ac6 · report fixture: signature args:MockArgs/0/?, line:str/0/str, tokenizer:MockTokenizer/0/? · returned tuple · level recorded 2026-09-24
get_collate_function income/jpq/dataset.py ran Apache-2.0 (permissive) · a9a03792761f628c · report fixture: signature max_seq_length:int/0/int · returned function · level recorded 2026-09-24
pack_tensor_2D income/jpq/dataset.py ran Apache-2.0 (permissive) · 7f738a55dde7b691 · report fixture: signature lstlst:list/1/list, default:float/0/float, dtype:dtype/0/?, length:NoneType/0/? · returned Tensor · level recorded 2026-09-24
pad_input_ids income/jpq/preprocess.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · b201d8d93b242b70 · report fixture: signature input_ids:list/1/int, max_length:int/0/int, pad_on_left:bool/0/bool, pad_token:int/0/int · returned list · level recorded 2026-09-24
multi_file_process income/jpq/preprocess.py unverified Apache-2.0 (permissive) · 7cc208c6b8263844 · report

Tasks

Contrastive LearningCross-Lingual TransferFact CheckingInformation RetrievalPassage RetrievalQuestion AnsweringRetrievalSentence Retrieval

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Passage Retrieval PeerQA Contriever-MS MRR 0.4408 #6 of 8 Archive leaderboard report
Passage Retrieval PeerQA Contriever-MS Recall@10 0.6314 #6 of 8 Archive leaderboard report
Passage Retrieval PeerQA Contriever MRR 0.3624 #8 of 8 Archive leaderboard report
Passage Retrieval PeerQA Contriever Recall@10 0.5567 #8 of 8 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.

Methods

Contrastive Learning

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