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

Papers archive 2025-07-28

30 shown of 1,286, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

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