In-Depth Analysis of Graph-Based RAG in a Unified Framework
Proceedings of the VLDB Endowment · 2025-09 · 18 (13) · 5623-5637
DOI: 10.14778/3773731.3773738 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the VLDB Endowment, online erschienen am 07.01.2026. Verfasst von Yingli Zhou und 10 weiteren Autor:innen. Die Arbeit wurde bisher 26-mal zitiert (Crossref) und nennt 99 Literaturangaben.
Abstract (Originalsprache)
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.
Zitieren
APA
Zhou, Y., Su, Y., Sun, Y., Wang, S., Wang, T., He, R., Zhang, Y., Liang, S., Liu, X., Ma, Y., & Fang, Y. (2025). In-Depth Analysis of Graph-Based RAG in a Unified Framework. Proceedings of the VLDB Endowment, 18(13), 5623-5637. https://doi.org/10.14778/3773731.3773738
Vancouver
Zhou Y, Su Y, Sun Y, Wang S, Wang T, He R, et al. In-Depth Analysis of Graph-Based RAG in a Unified Framework. Proceedings of the VLDB Endowment. 2025;18(13):5623-5637. doi:10.14778/3773731.3773738
BibTeX
@article{Zhou2025,
author = {Zhou, Yingli and Su, Yaodong and Sun, Youran and Wang, Shu and Wang, Taotao and He, Runyuan and Zhang, Yongwei and Liang, Sicong and Liu, Xilin and Ma, Yuchi and Fang, Yixiang},
title = {In-Depth Analysis of Graph-Based RAG in a Unified Framework},
journal = {Proceedings of the VLDB Endowment},
year = {2025},
volume = {18},
number = {13},
pages = {5623--5637},
doi = {10.14778/3773731.3773738}
}
EUVIMED