Self-RAG

anchor

Retrieval-augmented generation in which the model itself decides when to retrieve and critiques what it retrieved.

Findings

• IC-034Benefit and detriment in RAG can be traded off at token level for Llama-2, OPT and Mistral using representation similarity [compared-to]
• IC-174RAG reduces model abstention and LLMs hallucinate rather than abstain when the retrieved context is insufficient to answer the query [context]