LLMs Know What They Need: Leveraging a Missing Information Guided Framework to Empower Retrieval-Augmented Generation

arXiv:2404.14043v1 Announce Type: new
Abstract: Retrieval-Augmented Generation (RAG) demonstrates great value in alleviating outdated knowledge or hallucination by supplying LLMs with updated and relevant knowledge. However, there are still several difficulties for RAG in understanding complex multi-hop query and retrieving relevant documents, which require LLMs to perform reasoning and retrieve step by step. Inspired by human's reasoning process in which they gradually search for the required information, it is natural to ask whether the LLMs could notice the missing information …

abstract arxiv cs.cl documents framework hallucination however information knowledge llms query rag retrieval retrieval-augmented type understanding value