Plan-and-Refine in RAG: Generating Diverse and Comprehensive Responses through Global Exploration and Local Exploitation
This paper studies the limitations of (retrieval-augmented) large language models (LLMs) in generating diverse and comprehensive responses, and introduces the Plan-and-Refine (P&R) framework based on a two phase system design. In the global exploration phase, P&R generates a diverse set of plans for the given input, wh...