Query-Centric Graph Retrieval Augmented Generation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wu, Yaxiong, Bo, Jianyuan, Zhang, Yongyue, Liang, Sheng, Liu, Yong
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914056624930816
author Wu, Yaxiong
Bo, Jianyuan
Zhang, Yongyue
Liang, Sheng
Liu, Yong
author_facet Wu, Yaxiong
Bo, Jianyuan
Zhang, Yongyue
Liang, Sheng
Liu, Yong
contents Graph-based retrieval-augmented generation (RAG) enriches large language models (LLMs) with external knowledge for long-context understanding and multi-hop reasoning, but existing methods face a granularity dilemma: fine-grained entity-level graphs incur high token costs and lose context, while coarse document-level graphs fail to capture nuanced relations. We introduce QCG-RAG, a query-centric graph RAG framework that enables query-granular indexing and multi-hop chunk retrieval. Our query-centric approach leverages Doc2Query and Doc2Query{-}{-} to construct query-centric graphs with controllable granularity, improving graph quality and interpretability. A tailored multi-hop retrieval mechanism then selects relevant chunks via the generated queries. Experiments on LiHuaWorld and MultiHop-RAG show that QCG-RAG consistently outperforms prior chunk-based and graph-based RAG methods in question answering accuracy, establishing a new paradigm for multi-hop reasoning.
format Preprint
id arxiv_https___arxiv_org_abs_2509_21237
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Query-Centric Graph Retrieval Augmented Generation
Wu, Yaxiong
Bo, Jianyuan
Zhang, Yongyue
Liang, Sheng
Liu, Yong
Computation and Language
Information Retrieval
I.2.7; H.3.3
Graph-based retrieval-augmented generation (RAG) enriches large language models (LLMs) with external knowledge for long-context understanding and multi-hop reasoning, but existing methods face a granularity dilemma: fine-grained entity-level graphs incur high token costs and lose context, while coarse document-level graphs fail to capture nuanced relations. We introduce QCG-RAG, a query-centric graph RAG framework that enables query-granular indexing and multi-hop chunk retrieval. Our query-centric approach leverages Doc2Query and Doc2Query{-}{-} to construct query-centric graphs with controllable granularity, improving graph quality and interpretability. A tailored multi-hop retrieval mechanism then selects relevant chunks via the generated queries. Experiments on LiHuaWorld and MultiHop-RAG show that QCG-RAG consistently outperforms prior chunk-based and graph-based RAG methods in question answering accuracy, establishing a new paradigm for multi-hop reasoning.
title Query-Centric Graph Retrieval Augmented Generation
topic Computation and Language
Information Retrieval
I.2.7; H.3.3
url https://arxiv.org/abs/2509.21237