Aug 2026· Proceedings of the VLDB Endowment· Vol 19, pp. 4900-4905· 0 citations· 18 references
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.
This paper adopts a literature review approach to survey knowledge graph-enhanced GraphRAG, and analyzes the indexing, retrieval, and generation workflows, as well as key techniques including graph traversal, community summarization, hybrid retrieval, and graph-augmented generation.
Fan-Hao Zhou· Applied and Computational En...· 0 citations
PoP-RAG is proposed, which features a passage-on-edge (PoE) graph that links the passages with graph edges to resolve the one-to-many entity-passage mapping problem and enables targeted retrieval for each sub-query and ensures transparent response derivation logic, thus enhancing explainability.
Xin-Tong Hu, Qi-Ming Zeng, Yu-Hao Lin et al.· Transactions on Graph Intell...· 1 citation
LiteRAG is presented, a graph-based retrieval method that replaces expensive retrieval-time LLM control with query-conditioned algorithmic exploration and reasoning-chain context construction and attains the highest overall quality among the evaluated methods.
Daniel Alejandro Coll Tejeda, Pedro García López, Daniel Barcelona-Pons· 0 citations
This study constructs and comparatively analyzes Retrieval-Augmented Generation (RAG) and GraphRAG (RAPTOR RAG, Community-GraphRAG, HippoRAG2) systems based on university regulations to enhance administrative efficiency and knowledge management. Utilizing the Llama-3.1-8B language model and the text-embedding-ada-002 e...
Eun-Jin Jeon, Hoi-Jeong Lim· Korean Institute of Smart Me...· 0 citations
A novel framework KD-GAG is proposed that efficiently constructs KGs by distilling teacher LLMs' semantics and reasoning into a smaller student LLM and a preference-based subgraph pruning method to optimize the retrieval process.
Long Zhao, Yin Xu, Yan-Yan Wang et al.· Neural Networks· 0 citations
Integrating Knowledge Graphs (KGs) into Retrieval-Augmented Generation (RAG) can substantially improve LLM performance on complex question answering (QA) by reducing hallucinations and supplying structured context. However, building high-quality KGs over large corpora for edge scenarios is challenging: cloud-based proc...
Yuyu Du, Ju-Xin Niu, Chun Jason Xue et al.· IEEE International Conferenc...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.