XGraphRAG: Interactive Visual Analysis for Graph-based Retrieval-Augmented Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Ke, Pan, Bo, Feng, Yingchaojie, Wu, Yuwei, Chen, Jieyi, Zhu, Minfeng, Chen, Wei
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912433179721728
author Wang, Ke
Pan, Bo
Feng, Yingchaojie
Wu, Yuwei
Chen, Jieyi
Zhu, Minfeng
Chen, Wei
author_facet Wang, Ke
Pan, Bo
Feng, Yingchaojie
Wu, Yuwei
Chen, Jieyi
Zhu, Minfeng
Chen, Wei
contents Graph-based Retrieval-Augmented Generation (RAG) has shown great capability in enhancing Large Language Model (LLM)'s answer with an external knowledge base. Compared to traditional RAG, it introduces a graph as an intermediate representation to capture better structured relational knowledge in the corpus, elevating the precision and comprehensiveness of generation results. However, developers usually face challenges in analyzing the effectiveness of GraphRAG on their dataset due to GraphRAG's complex information processing pipeline and the overwhelming amount of LLM invocations involved during graph construction and query, which limits GraphRAG interpretability and accessibility. This research proposes a visual analysis framework that helps RAG developers identify critical recalls of GraphRAG and trace these recalls through the GraphRAG pipeline. Based on this framework, we develop XGraphRAG, a prototype system incorporating a set of interactive visualizations to facilitate users' analysis process, boosting failure cases collection and improvement opportunities identification. Our evaluation demonstrates the effectiveness and usability of our approach. Our work is open-sourced and available at https://github.com/Gk0Wk/XGraphRAG.
format Preprint
id arxiv_https___arxiv_org_abs_2506_13782
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle XGraphRAG: Interactive Visual Analysis for Graph-based Retrieval-Augmented Generation
Wang, Ke
Pan, Bo
Feng, Yingchaojie
Wu, Yuwei
Chen, Jieyi
Zhu, Minfeng
Chen, Wei
Information Retrieval
Artificial Intelligence
Graph-based Retrieval-Augmented Generation (RAG) has shown great capability in enhancing Large Language Model (LLM)'s answer with an external knowledge base. Compared to traditional RAG, it introduces a graph as an intermediate representation to capture better structured relational knowledge in the corpus, elevating the precision and comprehensiveness of generation results. However, developers usually face challenges in analyzing the effectiveness of GraphRAG on their dataset due to GraphRAG's complex information processing pipeline and the overwhelming amount of LLM invocations involved during graph construction and query, which limits GraphRAG interpretability and accessibility. This research proposes a visual analysis framework that helps RAG developers identify critical recalls of GraphRAG and trace these recalls through the GraphRAG pipeline. Based on this framework, we develop XGraphRAG, a prototype system incorporating a set of interactive visualizations to facilitate users' analysis process, boosting failure cases collection and improvement opportunities identification. Our evaluation demonstrates the effectiveness and usability of our approach. Our work is open-sourced and available at https://github.com/Gk0Wk/XGraphRAG.
title XGraphRAG: Interactive Visual Analysis for Graph-based Retrieval-Augmented Generation
topic Information Retrieval
Artificial Intelligence
url https://arxiv.org/abs/2506.13782