Retrieval-Augmented Generation
A family of system designs and methods that retrieve information from external sources and provide it to a language model during generation of an answer or other text.
Example
A system retrieves relevant pages from a policy collection for a question and supplies excerpts to the model before generating an answer.
Distinctions and cautions
RAG is an architectural approach or method; it does not guarantee that the correct information is retrieved, that answers are factually accurate, or that outputs are adequately supported by evidence. A RAG system can experience Retrieval Failure, and RAG is not synonymous with Grounding.
Evidence
View evidence →
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
- Title
- Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
- Author / organization
- Lewis et al.
- Year
- 2020
- Source type / publication status
- NeurIPS peer-reviewed research; published
- Supported concepts / claim context
- RAG definition; retrieval plus parametric generation; factuality benefit.
- Scope and limitations
- Describes the original RAG architecture, not every present-day RAG variation.
- Access / version note
- Published NeurIPS proceedings.
- Recorded official URL / DOI / identifier
- As recorded:
NeurIPS 2020 proceedings URL (exact URL not recorded here)(no URL inferred)
ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systems
- Title
- ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systems
- Author / organization
- Saad-Falcon et al.
- Year
- 2024
- Source type / publication status
- NAACL peer-reviewed research; published
- Supported concepts / claim context
- Context relevance, answer faithfulness, answer relevance, Retrieval Failure.
- Scope and limitations
- The evaluator design itself can introduce errors.
- Access / version note
- Published NAACL.
- Recorded official URL / DOI / identifier
- DOI:
10.18653/v1/2024.naacl-long.20(DOI resolver)
Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Models
- Title
- Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Models
- Author / organization
- Wang et al.
- Year
- 2025
- Source type / publication status
- ACL peer-reviewed research; published
- Supported concepts / claim context
- Retrieval Failure, RAG, Knowledge Conflict.
- Scope and limitations
- Controlled RAG analyses; no universal extrapolation to all retrievers or domains.
- Access / version note
- Published ACL.
- Recorded official URL / DOI / identifier
- DOI:
10.18653/v1/2025.acl-long.1476(DOI resolver)