2025
Retrieval is Not Enough: Enhancing RAG through Test-Time Critique and Optimization
NeurIPS 2025poster
Retrieval-augmented generation (RAG) has become a widely adopted paradigm for enabling knowledge-grounded large language models (LLMs). However, standard RAG pipelines often fail to ensure that model reasoning remains consistent with the evidence retrieved, leading to factual inconsistencies or unsu…