In-depth Analysis of Graph-based RAG in a Unified Framework
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911624071217152 |
|---|---|
| author | Zhou, Yingli Su, Yaodong Sun, Youran Wang, Shu Wang, Taotao He, Runyuan Zhang, Yongwei Liang, Sicong Liu, Xilin Ma, Yuchi Fang, Yixiang |
| author_facet | Zhou, Yingli Su, Yaodong Sun, Youran Wang, Shu Wang, Taotao He, Runyuan Zhang, Yongwei Liang, Sicong Liu, Xilin Ma, Yuchi Fang, Yixiang |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_04338 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | In-depth Analysis of Graph-based RAG in a Unified Framework Zhou, Yingli Su, Yaodong Sun, Youran Wang, Shu Wang, Taotao He, Runyuan Zhang, Yongwei Liang, Sicong Liu, Xilin Ma, Yuchi Fang, Yixiang Information Retrieval Computation and Language Databases 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. |
| title | In-depth Analysis of Graph-based RAG in a Unified Framework |
| topic | Information Retrieval Computation and Language Databases |
| url | https://arxiv.org/abs/2503.04338 |