Graph-Based Retrieval-Augmented Generation: Applications, Challenges, Solutions, and Opportunities
TL;DR
This tutorial outlines the core pipeline stages of graph-based RAG and analyze them from a data management perspective, including graph modeling, graph repair, index construction and maintenance, and retrieval, rather than treating graph-based RAG solely as an LLM application.
Abstract
Graph-Based Retrieval-Augmented Generation (RAG) has proven effective in integrating structured external knowledge into Large Language Models (LLMs), improving their factual accuracy, adaptability, interpretability, and trustworthiness. Accordingly, a large number of graph-based RAG methods have been proposed in recent years by the database, data mining, machine learning, and natural language processing communities. In this tutorial, we first highlight the real-world applications of graph-based RAG and the unique challenges that need to be addressed. We then classify and compare representative graph-based RAG methods from well-known top data management and data mining venues. Afterward, we outline the core pipeline stages of graph-based RAG and analyze them from a data management perspective, including graph modeling, graph repair, index construction and maintenance, and retrieval, rather than treating graph-based RAG solely as an LLM application. Finally, we discuss how graph-based RAG can be extended to multimodal data and identify promising future research directions.