FlexStructRAG: Flexible Structure-Aware Multi-Granular Relational Retrieval for RAG

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Chen, Mengzhu, Yang, Haodong, Cai, Jia, Huang, Xiaolin
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908974832418816
author Chen, Mengzhu
Yang, Haodong
Cai, Jia
Huang, Xiaolin
author_facet Chen, Mengzhu
Yang, Haodong
Cai, Jia
Huang, Xiaolin
contents Retrieval-Augmented Generation (RAG) systems critically depend on how external knowledge is segmented, structured, and retrieved. Most existing approaches either retrieve fixed-length text chunks, which fragments discourse context, or commit to a single structured index (e.g., a knowledge graph or hypergraph), which hard-codes one relational granularity. This often yields brittle retrieval when queries require different forms of evidence, such as local binary relations, higher-order interactions, or broader document-grounded context. We propose \textbf{FlexStructRAG}, a flexible structure-aware RAG framework that supports \emph{multi-granular, query-adaptive retrieval} over heterogeneous knowledge representations. FlexStructRAG jointly constructs (i) a knowledge graph for binary relations, (ii) a knowledge hypergraph for n-ary relations, and (iii) structure-aware semantic clusters that aggregate relational evidence into document-grounded context units. To reduce semantic fragmentation induced by uniform chunking, we introduce dynamic partitioning and a truncated sliding-window extraction mechanism that incorporates bounded contextual dependencies during knowledge construction. At inference time, FlexStructRAG enables entity-, edge-, hyperedge-, and cluster-level retrieval, which can be flexibly combined to supply generation with relationally and contextually aligned evidence. Experiments on the UltraDomain benchmark across four domains show that FlexStructRAG improves semantic evaluation over strong RAG baselines. Ablation and sensitivity analysis further demonstrate the necessity of multi-granular relational retrieval and structure-aware clustering.
format Preprint
id arxiv_https___arxiv_org_abs_2604_16312
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle FlexStructRAG: Flexible Structure-Aware Multi-Granular Relational Retrieval for RAG
Chen, Mengzhu
Yang, Haodong
Cai, Jia
Huang, Xiaolin
Information Retrieval
Artificial Intelligence
I.2.7
Retrieval-Augmented Generation (RAG) systems critically depend on how external knowledge is segmented, structured, and retrieved. Most existing approaches either retrieve fixed-length text chunks, which fragments discourse context, or commit to a single structured index (e.g., a knowledge graph or hypergraph), which hard-codes one relational granularity. This often yields brittle retrieval when queries require different forms of evidence, such as local binary relations, higher-order interactions, or broader document-grounded context. We propose \textbf{FlexStructRAG}, a flexible structure-aware RAG framework that supports \emph{multi-granular, query-adaptive retrieval} over heterogeneous knowledge representations. FlexStructRAG jointly constructs (i) a knowledge graph for binary relations, (ii) a knowledge hypergraph for n-ary relations, and (iii) structure-aware semantic clusters that aggregate relational evidence into document-grounded context units. To reduce semantic fragmentation induced by uniform chunking, we introduce dynamic partitioning and a truncated sliding-window extraction mechanism that incorporates bounded contextual dependencies during knowledge construction. At inference time, FlexStructRAG enables entity-, edge-, hyperedge-, and cluster-level retrieval, which can be flexibly combined to supply generation with relationally and contextually aligned evidence. Experiments on the UltraDomain benchmark across four domains show that FlexStructRAG improves semantic evaluation over strong RAG baselines. Ablation and sensitivity analysis further demonstrate the necessity of multi-granular relational retrieval and structure-aware clustering.
title FlexStructRAG: Flexible Structure-Aware Multi-Granular Relational Retrieval for RAG
topic Information Retrieval
Artificial Intelligence
I.2.7
url https://arxiv.org/abs/2604.16312