AI Governance Engineer
GitHub

Retrieval-augmented generation (RAG)

By Updated

A system that combines a model's learned memory with a retrievable store of documents at answer time 1. The corpus becomes behaviour, so it is governed like a model: versioned, carded, tied to the eval that tested it, with an entitlement check on what each user may retrieve.

Developed in
ch. 11, RAG systems
Chapters
ch. 11, AI Defined · ch. 16, Fairness & XAI
Source
1 numbered reference, listed below

Where it is used

8 chapters of the Body of Knowledge use the term. Each link opens the first section that does.

Sources

  1. [1] Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks (parametric and non-parametric memory; arXiv 2005.11401). Lewis et al.. 2020-05-22. https://arxiv.org/abs/2005.11401 (verified: primary)

Definitions of legal terms paraphrase the cited text, which governs. Dated statements are as of .

Cite this term

García Aibar, J. (2026). Retrieval-augmented generation (RAG). In AI Governance Engineering: The Thesis & Body of Knowledge (v0.5.0), Glossary. https://doi.org/10.5281/zenodo.22956197. https://aigovernanceengineer.com/glossary/retrieval-augmented-generation-rag. CC BY 4.0

BibTeX

@misc{aige2026retrievalaugmentedgenerationrag,
  author  = {Jorge García Aibar},
  title   = {{Retrieval-augmented generation (RAG)}},
  note    = {Glossary, AI Governance Engineering: The Thesis \& Body of Knowledge, version 0.5.0},
  year    = {2026},
  doi     = {10.5281/zenodo.22956197},
  url     = {https://aigovernanceengineer.com/glossary/retrieval-augmented-generation-rag}
}