Retrieval-Augmented Generation for Large Language Models: A Survey

TL;DR

This survey comprehensively reviews Retrieval-Augmented Generation (RAG) methods for large language models, highlighting advancements, evaluation benchmarks, and future research directions to address issues like hallucination and knowledge updating.

Contribution

It provides a detailed analysis of RAG paradigms, components, state-of-the-art technologies, and introduces new evaluation frameworks and benchmarks.

Findings

RAG improves LLM accuracy and credibility.

New evaluation benchmarks for RAG systems.

Identification of challenges and future research directions.

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Large Language Models (LLMs) showcase impressive capabilities but encounter challenges like hallucination, outdated knowledge, and non-transparent, untraceable reasoning processes.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 paper offers a detailed examination of the progression of RAG paradigms, encompassing the Naive RAG, the Advanced RAG, and the Modular RAG. It meticulously scrutinizes the tripartite foundation of RAG frameworks, which includes the retrieval, the generation and the augmentation techniques. The paper highlights the state-of-the-art technologies embedded in each of these critical components, providing a profound understanding of the advancements in RAG systems. Furthermore, this paper introduces up-to-date evaluation framework and benchmark. At the end, this article delineates the challenges currently faced and points out prospective avenues for research and development.