Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection

by University of Washington / IBM AI Research / Allen AI · free · Last verified 2026-03-17

Introduces Self-RAG, a framework that trains a single LM to adaptively retrieve passages on demand, generate text, and critique its own outputs using special reflection tokens. Unlike standard RAG, Self-RAG decides when to retrieve and reflects on retrieved passages and generation quality, outperforming ChatGPT and standard RAG on diverse downstream tasks.