Graph Retrieval-Augmented Generation: A Survey

TL;DR

This survey comprehensively reviews Graph Retrieval-Augmented Generation (GraphRAG), highlighting its workflow, core technologies, applications, and future directions to enhance knowledge retrieval in large language models.

Contribution

First systematic overview of GraphRAG methodologies, formalizing its workflow and analyzing core technologies, tasks, and applications in the field.

Findings

GraphRAG improves retrieval accuracy by leveraging structural entity relationships.

Core technologies include graph-based indexing and graph-guided retrieval.

Applications span various domains with promising industrial use cases.

Abstract

Recently, Retrieval-Augmented Generation (RAG) has achieved remarkable success in addressing the challenges of Large Language Models (LLMs) without necessitating retraining. By referencing an external knowledge base, RAG refines LLM outputs, effectively mitigating issues such as ``hallucination'', lack of domain-specific knowledge, and outdated information. However, the complex structure of relationships among different entities in databases presents challenges for RAG systems. In response, GraphRAG leverages structural information across entities to enable more precise and comprehensive retrieval, capturing relational knowledge and facilitating more accurate, context-aware responses. Given the novelty and potential of GraphRAG, a systematic review of current technologies is imperative. This paper provides the first comprehensive overview of GraphRAG methodologies. We formalize the GraphRAG workflow, encompassing Graph-Based Indexing, Graph-Guided Retrieval, and Graph-Enhanced Generation. We then outline the core technologies and training methods at each stage. Additionally, we examine downstream tasks, application domains, evaluation methodologies, and industrial use cases of GraphRAG. Finally, we explore future research directions to inspire further inquiries and advance progress in the field. In order to track recent progress in this field, we set up a repository at \url{https://github.com/pengboci/GraphRAG-Survey}.