Methods › Natural Language Processing › Transformers › RAG

RAG

1,286 papers tagged archive 2025-07-28

Introduced by Patrick Lewis et al. in Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

Retriever-Augmented Generation, or RAG, is a type of language generation model that combines pre-trained parametric and non-parametric memory for language generation. Specifically, 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. For query x, Maximum Inner Product Search (MIPS) is used to find the top-K documents zᵢ. For final prediction y, we treat z as a latent variable and marginalize over seq2seq predictions given different documents.

PaperSource

In Syntology repository known, no verified implementation (declared_code; repositories: 5 listed of 18 in the graph, strongest link: official). This answer is about arXiv:2005.11401, the paper the archive credits with this method.

Code Syntology holds under other names, as the lookup lists them (code_nearby); not a complete list, and none of them is this method.

Origin paper of this answer, arXiv:2005.11401 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 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 (of 6 harvested samples). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.

Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.

What each level means, quoted from Syntology's server card: V0 “imports”; V1 “executes against a synthesized fixture and returns a value of the recorded type”; V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” The card adds: “No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results.” A level quoted in two parts is one definition the card writes as two clauses joined by a double hyphen, each clause quoted on its own (how these levels are quoted).

Papers archive 2025-07-28

archive papers tagged: 1,286 · with a code link: 488 · where Syntology ran a sample: 144 (112 with a run with no instrument failure, 32 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (144 of 1,286 tagged: 112 with a run with no instrument failure, 32 where every run was a failure of Syntology's instrument)

Page 1 of 13: papers 1 to 100 of 1,286, newest first by the archive's date (ties by slug), in archive order.

Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.

Tasks archive 2025-07-28

20 shown of 363 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
RAG1,281
Retrieval-augmented Generation1,083
Retrieval943
Question Answering315
Language Modelling137
Large Language Model123
Language Modeling116
Hallucination114
Information Retrieval104
Benchmarking52
Knowledge Graphs52
Text Generation51
Answer Generation39
Reranking35
Chunking34
Response Generation34
Open-Domain Question Answering30
Decision Making29
Prompt Engineering29
In-Context Learning27

Usage over time archive 2025-07-28

Papers per year tagged with RAG: 2020 to 2025, peak 682 682 0 2020: 2 papers 2020 2021: 5 papers 2021 2022: 7 papers 2022 2023: 35 papers 2023 2024: 682 papers 2024 2025: 555 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (1,286 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Transformers

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