Papers › REALM: Retrieval-Augmented Language Model Pre-Training

REALM: Retrieval-Augmented Language Model Pre-Training

10 Feb 2020arXiv:2002.08909archive 2025-07-28

Kelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat, Ming-Wei Chang

Language model pre-training has been shown to capture a surprising amount of world knowledge, crucial for NLP tasks such as question answering. However, this knowledge is stored implicitly in the parameters of a neural network, requiring ever-larger networks to cover more facts. To capture knowledge in a more modular and interpretable way, we augment language model pre-training with a latent knowledge retriever, which allows the model to retrieve and attend over documents from a large corpus such as Wikipedia, used during pre-training, fine-tuning and inference. For the first time, we show how to pre-train such a knowledge retriever in an unsupervised manner, using masked language modeling as the learning signal and backpropagating through a retrieval step that considers millions of documents. We demonstrate the effectiveness of Retrieval-Augmented Language Model pre-training (REALM) by fine-tuning on the challenging task of Open-domain Question Answering (Open-QA). We compare against state-of-the-art models for both explicit and implicit knowledge storage on three popular Open-QA benchmarks, and find that we outperform all previous methods by a significant margin (4-16% absolute accuracy), while also providing qualitative benefits such as interpretability and modularity.

PaperPDFCodeCode 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="2002.08909")

Code

Syntology Ran 4 of 4 code samples harvested from 2 repositories linked to this paper; 0 have no recorded run. Of those that ran: 2 ran · violated contract; 1 ran · our draft was wrong; 1 ran with no contract checked.

By repository: community (archive-listed): 4 samples from 2 repositories, 4 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Zefty/rag-end2end-retriever mentioned on GitHubpytorchnot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-ready report
deepset-ai/haystack mentioned on GitHubpytorchApache-2.0 report
lucidrains/mlm-pytorch mentioned on GitHubpytorch report
martiansideofthemoon/relic-retrieval mentioned on GitHubpytorch report
snjstudent/MyREALM mentioned on GitHubtf 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

4 samples harvested; 4 ran; 0 honoured the contract we drafted; 0 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.

2ran · violated contract
1ran · our draft was wrong
1ran

Licence: 0 of the 4 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 2 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.

PrefixSuffixModel martiansideofthemoon/relic-retrieval/retriever_train/utils.py community (archive-listed) ran MIT (permissive) · 3b2b6f543ceae53e · report
get_mask_subset_with_prob lucidrains/mlm-pytorch/mlm_pytorch/mlm_pytorch.py community (archive-listed) ran · violated contract MIT (permissive) · e33ada12822bb56c · report
mask_with_tokens lucidrains/mlm-pytorch/mlm_pytorch/mlm_pytorch.py community (archive-listed) ran · violated contract fingerprinted MIT (permissive) · 5573a79bdc0a0a09 · report
prob_mask_like lucidrains/mlm-pytorch/mlm_pytorch/mlm_pytorch.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 0a27e49623646a01 · report

Tasks

Language ModelingLanguage ModellingMasked Language ModelingOpen-Domain Question AnsweringQuestion AnsweringRetrievalWorld Knowledgemodel

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Question Answering Natural Questions REALM EM 40.4 #24 of 47 Archive leaderboard report
Question Answering WebQuestions REALM EM 40.7 #19 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.

Methods

Interpretability

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