DA-RAG: Dynamic Attributed Community Search for Retrieval-Augmented Generation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zeng, Xingyuan, Wu, Zuohan, Wang, Yue, Zhang, Chen, Yao, Quanming, Zheng, Libin, Yin, Jian
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914315630542848
author Zeng, Xingyuan
Wu, Zuohan
Wang, Yue
Zhang, Chen
Yao, Quanming
Zheng, Libin
Yin, Jian
author_facet Zeng, Xingyuan
Wu, Zuohan
Wang, Yue
Zhang, Chen
Yao, Quanming
Zheng, Libin
Yin, Jian
contents Owing to their unprecedented comprehension capabilities, large language models (LLMs) have become indispensable components of modern web search engines. From a technical perspective, this integration represents retrieval-augmented generation (RAG), which enhances LLMs by grounding them in external knowledge bases. A prevalent technical approach in this context is graph-based RAG (G-RAG). However, current G-RAG methodologies frequently underutilize graph topology, predominantly focusing on low-order structures or pre-computed static communities. This limitation affects their effectiveness in addressing dynamic and complex queries. Thus, we propose DA-RAG, which leverages attributed community search (ACS) to extract relevant subgraphs based on the queried question dynamically. DA-RAG captures high-order graph structures, allowing for the retrieval of self-complementary knowledge. Furthermore, DA-RAG is equipped with a chunk-layer oriented graph index, which facilitates efficient multi-granularity retrieval while significantly reducing both computational and economic costs. We evaluate DA-RAG on multiple datasets, demonstrating that it outperforms existing RAG methods by up to 40% in head-to-head comparisons across four metrics while reducing index construction time and token overhead by up to 37% and 41%, respectively.
format Preprint
id arxiv_https___arxiv_org_abs_2602_08545
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle DA-RAG: Dynamic Attributed Community Search for Retrieval-Augmented Generation
Zeng, Xingyuan
Wu, Zuohan
Wang, Yue
Zhang, Chen
Yao, Quanming
Zheng, Libin
Yin, Jian
Information Retrieval
Owing to their unprecedented comprehension capabilities, large language models (LLMs) have become indispensable components of modern web search engines. From a technical perspective, this integration represents retrieval-augmented generation (RAG), which enhances LLMs by grounding them in external knowledge bases. A prevalent technical approach in this context is graph-based RAG (G-RAG). However, current G-RAG methodologies frequently underutilize graph topology, predominantly focusing on low-order structures or pre-computed static communities. This limitation affects their effectiveness in addressing dynamic and complex queries. Thus, we propose DA-RAG, which leverages attributed community search (ACS) to extract relevant subgraphs based on the queried question dynamically. DA-RAG captures high-order graph structures, allowing for the retrieval of self-complementary knowledge. Furthermore, DA-RAG is equipped with a chunk-layer oriented graph index, which facilitates efficient multi-granularity retrieval while significantly reducing both computational and economic costs. We evaluate DA-RAG on multiple datasets, demonstrating that it outperforms existing RAG methods by up to 40% in head-to-head comparisons across four metrics while reducing index construction time and token overhead by up to 37% and 41%, respectively.
title DA-RAG: Dynamic Attributed Community Search for Retrieval-Augmented Generation
topic Information Retrieval
url https://arxiv.org/abs/2602.08545