Retrieval-Augmented Generation (RAG)
Retrieval-augmented generation is a technique that grounds a language model's output in retrieved source documents instead of relying solely on its parametric memory. The system fetches relevant passages from a knowledge base, supplies them as context, and asks the model to answer using only that evidence.
Synonyms: RAG, retrieval augmented generation, grounded generation, context augmentation
Retrieval-augmented generation separates what a model knows from what it was trained on. At query time the retriever pulls the most relevant chunks from a maintained knowledge base, and the model composes an answer constrained to that evidence. This reduces hallucination, makes answers auditable through citations, and lets teams update knowledge without retraining. In a governed setting, RAG is the mechanism that turns a question into a grounded, cited response that a person or policy can verify before it is trusted.