rag-lewis-2020
IN premise — entries/2026/06/21/wiki-Large_language_model-chunk-5.md
Created 2026-06-21T09:50:09+00:00
Retrieval-Augmented Generation (RAG) was introduced by Lewis et al. in 2020, combining retrieval with generation to reduce hallucination
Summary
The system records that the approach of having a language model pull in relevant external documents before composing an answer was first proposed by Lewis and colleagues in 2020, with the explicit goal of making outputs more factually grounded and less prone to fabrication. This serves as the origin point for any downstream reasoning about RAG's intended benefits, its architectural assumptions, or its limitations.