Retrieval-Augmented Generation for Large Language Models: A Survey

arXiv:2312.10997v5 Announce Type: replace
Abstract: Large Language Models (LLMs) showcase impressive capabilities but encounter challenges like hallucination, outdated knowledge, and non-transparent, untraceable reasoning processes. Retrieval-Augmented Generation (RAG) has emerged as a promising solution by incorporating knowledge from external databases. This enhances the accuracy and credibility of the generation, particularly for knowledge-intensive tasks, and allows for continuous knowledge updates and integration of domain-specific information. RAG synergistically merges LLMs' intrinsic knowledge with the vast, dynamic repositories of external databases. This comprehensive review …

abstract accuracy arxiv capabilities challenges cs.ai cs.cl databases hallucination knowledge language language models large language large language models llms processes rag reasoning retrieval retrieval-augmented solution survey tasks transparent type