In-Depth Analysis of Graph-Based RAG in a Unified Framework
Authors:
Open Access
- 1 September 2025
- journal article
- Published by Association for Computing Machinery (ACM) in Proceedings of the VLDB Endowment
- Vol. 18 (13) , 5623-5637
Abstract
Graph-based Retrieval-Augmented Generation (RAG) has proven effective in integrating external knowledge into large language models (LLMs), improving their factual accuracy, adaptability, interpretability, and trustworthiness. A number of graph-based RAG methods have been proposed in the literature. However, these methods have not been systematically and comprehensively compared under the same experimental settings. In this paper, we first summarize a unified framework to incorporate all graph-based RAG methods from a high-level perspective. We then extensively compare representative graph-based RAG methods over a range of questing-answering (QA) datasets - from specific questions to abstract questions - and examine the effectiveness of all methods, providing a thorough analysis of graph-based RAG approaches. As a byproduct of our experimental analysis, we are also able to identify new variants of the graph-based RAG methods over specific QA and abstract QA tasks respectively, by combining existing techniques, which outperform the state-of-the-art methods. Finally, based on these findings, we offer promising research opportunities. We believe that a deeper understanding of the behavior of existing methods can provide new valuable insights for future research.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models2024
- Auto-Formula: Recommend Formulas in Spreadsheets using Contrastive Learning for Table RepresentationsProceedings of the ACM on Management of Data, 2024
- Cost-Effective In-Context Learning for Entity Resolution: A Design Space Exploration2024
- DB-GPT: Large Language Model Meets DatabaseData Science and Engineering, 2024
- Large Language Models in Finance: A Survey2023
- HAIPipe: Combining Human-generated and Machine-generated Pipelines for Data PreparationProceedings of the ACM on Management of Data, 2023
- Improving the Domain Adaptation of Retrieval Augmented Generation (RAG) Models for Open Domain Question AnsweringTransactions of the Association for Computational Linguistics, 2023
- ♫ MuSiQue: Multihop Questions via Single-hop Question CompositionTransactions of the Association for Computational Linguistics, 2022
- ColBERT2020
- Topic-sensitive PageRank2002