T-Retriever: Tree-based Hierarchical Retrieval Augmented Generation for Textual Graphs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wei, Chunyu, Qin, Huaiyu, He, Siyuan, Wang, Yunhai, Chen, Yueguo
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917190598393856
author Wei, Chunyu
Qin, Huaiyu
He, Siyuan
Wang, Yunhai
Chen, Yueguo
author_facet Wei, Chunyu
Qin, Huaiyu
He, Siyuan
Wang, Yunhai
Chen, Yueguo
contents Retrieval-Augmented Generation (RAG) has significantly enhanced Large Language Models' ability to access external knowledge, yet current graph-based RAG approaches face two critical limitations in managing hierarchical information: they impose rigid layer-specific compression quotas that damage local graph structures, and they prioritize topological structure while neglecting semantic content. We introduce T-Retriever, a novel framework that reformulates attributed graph retrieval as tree-based retrieval using a semantic and structure-guided encoding tree. Our approach features two key innovations: (1) Adaptive Compression Encoding, which replaces artificial compression quotas with a global optimization strategy that preserves the graph's natural hierarchical organization, and (2) Semantic-Structural Entropy ($S^2$-Entropy), which jointly optimizes for both structural cohesion and semantic consistency when creating hierarchical partitions. Experiments across diverse graph reasoning benchmarks demonstrate that T-Retriever significantly outperforms state-of-the-art RAG methods, providing more coherent and contextually relevant responses to complex queries.
format Preprint
id arxiv_https___arxiv_org_abs_2601_04945
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle T-Retriever: Tree-based Hierarchical Retrieval Augmented Generation for Textual Graphs
Wei, Chunyu
Qin, Huaiyu
He, Siyuan
Wang, Yunhai
Chen, Yueguo
Artificial Intelligence
Retrieval-Augmented Generation (RAG) has significantly enhanced Large Language Models' ability to access external knowledge, yet current graph-based RAG approaches face two critical limitations in managing hierarchical information: they impose rigid layer-specific compression quotas that damage local graph structures, and they prioritize topological structure while neglecting semantic content. We introduce T-Retriever, a novel framework that reformulates attributed graph retrieval as tree-based retrieval using a semantic and structure-guided encoding tree. Our approach features two key innovations: (1) Adaptive Compression Encoding, which replaces artificial compression quotas with a global optimization strategy that preserves the graph's natural hierarchical organization, and (2) Semantic-Structural Entropy ($S^2$-Entropy), which jointly optimizes for both structural cohesion and semantic consistency when creating hierarchical partitions. Experiments across diverse graph reasoning benchmarks demonstrate that T-Retriever significantly outperforms state-of-the-art RAG methods, providing more coherent and contextually relevant responses to complex queries.
title T-Retriever: Tree-based Hierarchical Retrieval Augmented Generation for Textual Graphs
topic Artificial Intelligence
url https://arxiv.org/abs/2601.04945