Papers › Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks

Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks

22 May 2020NeurIPS 2020 12arXiv:2005.11401archive 2025-07-28

Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, Sebastian Riedel, Douwe Kiela

Large pre-trained language models have been shown to store factual knowledge in their parameters, and achieve state-of-the-art results when fine-tuned on downstream NLP tasks. However, their ability to access and precisely manipulate knowledge is still limited, and hence on knowledge-intensive tasks, their performance lags behind task-specific architectures. Additionally, providing provenance for their decisions and updating their world knowledge remain open research problems. Pre-trained models with a differentiable access mechanism to explicit non-parametric memory can overcome this issue, but have so far been only investigated for extractive downstream tasks. We explore a general-purpose fine-tuning recipe for retrieval-augmented generation (RAG) -- models which combine pre-trained parametric and non-parametric memory for language generation. We introduce RAG models where the parametric memory is a pre-trained seq2seq model and the non-parametric memory is a dense vector index of Wikipedia, accessed with a pre-trained neural retriever. We compare two RAG formulations, one which conditions on the same retrieved passages across the whole generated sequence, the other can use different passages per token. We fine-tune and evaluate our models on a wide range of knowledge-intensive NLP tasks and set the state-of-the-art on three open domain QA tasks, outperforming parametric seq2seq models and task-specific retrieve-and-extract architectures. For language generation tasks, we find that RAG models generate more specific, diverse and factual language than a state-of-the-art parametric-only seq2seq baseline.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

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

Syntology 6 code samples harvested from 3 repositories linked to this paper: 6 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 6 samples from 3 repositories, 6 ran (5 with no instrument failure; 1 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 7 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

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

Zefty/rag-end2end-retriever mentioned on GitHubpytorchnot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-readySyntology: not harvested report
amaiya/onprem mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (1 instrument-failed) · 0 unverified report
assafelovic/gpt-researcher mentioned on GitHubSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
docarray/docarray mentioned on GitHubjaxApache-2.0Syntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
huggingface/transformers mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Attention Is All You Need (arXiv:1706.03762; that paper's own run record: 610 ran (of which 293 constructed an object rather than computing a result; 529 with no instrument failure: 45 honoured, 15 violated, 469 with no contract checked; 81 where Syntology's instrument failed) · 336 unverified), HuggingFace's Transformers: State-of-the-art Natural Language Processing (arXiv:1910.03771; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified), DeBERTa: Decoding-enhanced BERT with Disentangled Attention (arXiv:2006.03654; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
robotics-4-all/ISSEL-Announcements mentioned on GitHubSyntology: not harvested report
thu-keg/korc mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to KoRC: Knowledge oriented Reading Comprehension Benchmark for Deep Text Understanding (arXiv:2307.03115; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified) and ACL Anthology id 2023.findings-acl.743 (that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
MindSpore-scientific-2/code-10 mindsporeApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Normalizing Flows are Capable Generative Models (arXiv:2412.06329; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
MindSpore-scientific-2/code-4 mindsporeSyntology: not harvested report
MindSpore-scientific-2/code-5 mindsporeSyntology: not harvested report
MindSpore-scientific-2/code-8 mindsporeApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to LP-MusicCaps: LLM-Based Pseudo Music Captioning (arXiv:2307.16372; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
MindSpore-scientific-2/code-8 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to LP-MusicCaps: LLM-Based Pseudo Music Captioning (arXiv:2307.16372; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
bangoc123/drop-rag Syntology: not harvested report
bangoc123/retrieval-backend-with-rag Syntology: not harvested report
deepset-ai/haystack pytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Fabricator: An Open Source Toolkit for Generating Labeled Training Data with Teacher LLMs (arXiv:2309.09582; that paper's own run record: 17 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
lyqcom/mindspore_nlp_tutorial mindsporeMITSyntology: not harvested report
mindspore-courses/d2l-mindspore mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to SqueezeBERT: What can computer vision teach NLP about efficient neural networks? (arXiv:2006.11316; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
yangyucheng000/University mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution (arXiv:2409.12191; that paper's own run record: 12 ran (of which 1 constructed an object rather than computing a result; 10 with no instrument failure: 4 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. 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

6 samples harvested: 6 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 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.

1ran · our draft was wrong
5ran

Licence: 0 of the 6 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 3 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

amaiya/onprem community (archive-listed) 3 samples, 3 ran (1 instrument-failed) · 0 unverified
RAGPipeline onprem/pipelines/rag.py ran Apache-2.0 (permissive) · 97232ee5cefc6ca0 · report fixture: returned RAGPipeline · level recorded 2026-09-22
SafeFormatter onprem/pipelines/rag.py ran Apache-2.0 (permissive) · 0e37c1a090eb1522 · report fixture: returned SafeFormatter · level recorded 2026-09-22
format_string in 6 papers onprem/pipelines/rag.py ran · our draft was wrong Apache-2.0 (permissive) · b5b35b915ca92dc5 · report fixture: signature string_to_format:str/0/str, name:str/0/str, age:str/0/str · returned str · level recorded 2026-09-22
assafelovic/gpt-researcher community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
SearchAPIRetriever gpt_researcher/context/retriever.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 8ebc0b59ac8e1139 · report fixture: returned SearchAPIRetriever · level recorded 2026-09-22
docarray/docarray community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
get_paths in 32 papers docarray/helper.py ran Apache-2.0 (permissive) · f54f8f538675cd65 · report fixture: signature patterns:str/0/str, recursive:bool/0/bool, size:NoneType/0/?, exclude_regex:NoneType/0/? · returned generator · level recorded 2026-09-24
identity in 174 papers
census: 11 implementations from 39 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
docarray/computation/numpy_backend.py ran fingerprinted Apache-2.0 (permissive) · e855f42db656867c · report fixture: signature array:ndarray/2/float · returned ndarray · level recorded 2026-09-24

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

2 assemblies on this paper: 2 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

2 sibling assemblies for RAG (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for RAG (graph method: RAG). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 2 siblings

  1. SearchAPIRetriever entry · level 1 · ran · 8ebc0b59ac8e1139

harvested Assembly for RAG (graph method: RAG). 3 bricks; individually on a fixture: 3 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. RAGPipeline entry · level 1 · ran · 97232ee5cefc6ca0
  2. SafeFormatter helper · level 1 · ran · 0e37c1a090eb1522
  3. format_string helper · level 1 · ran · our draft was wrong · b5b35b915ca92dc5

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2005.11401") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Fact VerificationQuestion AnsweringRAGRetrievalRetrieval-augmented GenerationText GenerationWorld Knowledge

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Fact Verification FEVER RAG Accuracy 72.5 #6 of 7 Archive leaderboard report
Question Answering Natural Questions RAG EM 44.5 #19 of 47 Archive leaderboard report
Question Answering TriviaQA RAG EM 56.1 #43 of 56 Archive leaderboard report
Question Answering WebQuestions RAG EM 45.2 #8 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

Introduced by this paper: RAG

AdamAttentionAttention DropoutBARTBERTBPEDense ConnectionsDropoutLSTMLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionRAGResidual ConnectionSeq2SeqSigmoid ActivationSoftmaxTanh ActivationWeight DecayWordPiece

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