CONFLARE: CONFormal LArge language model REtrieval

arXiv:2404.04287v1 Announce Type: new
Abstract: Retrieval-augmented generation (RAG) frameworks enable large language models (LLMs) to retrieve relevant information from a knowledge base and incorporate it into the context for generating responses. This mitigates hallucinations and allows for the updating of knowledge without retraining the LLM. However, RAG does not guarantee valid responses if retrieval fails to identify the necessary information as the context for response generation. Also, if there is contradictory content, the RAG response will likely reflect only one …

abstract arxiv context cs.ai cs.cl frameworks hallucinations however information knowledge knowledge base language language model language models large language large language model large language models llm llms rag responses retraining retrieval retrieval-augmented type