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

• URL: http://arxiv.org/abs/2601.04945v1
• Date: Thu, 08 Jan 2026 13:49:12 GMT
• Title: T-Retriever: Tree-based Hierarchical Retrieval Augmented Generation for Textual Graphs
• Authors: Chunyu Wei, Huaiyu Qin, Siyuan He, Yunhai Wang, Yueguo Chen,
• Abstract summary: Graph-based RAG approaches impose rigid layer-specific compression quotas that damage local graph structures.<n>We introduce T-Retriever, a novel framework that reformulates graph retrieval as tree-based.<n>T-Retriever significantly outperforms state-of-the-art RAG methods, providing more coherent and contextually relevant responses to complex queries.
• Score: 14.797057622726037
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Topology of Reasoning: Retrieved Cell Complex-Augmented Generation for Textual Graph Question Answering [13.616604189732262]
  Topology-enhanced Retrieval-Augmented Generation (TopoRAG) is a novel framework for textual graph question answering.<n>TopoRAG first lifts textual graphs into cellular complexes to model multi-dimensional topological structures.<n>A multi-dimensional topological reasoning mechanism operates over these complexes to propagate relational information.
  arXiv  Detail & Related papers  (2026-02-22T15:44:53Z)
• Improving LLM Reasoning with Homophily-aware Structural and Semantic Text-Attributed Graph Compression [55.51959317490934]
  Large language models (LLMs) have demonstrated promising capabilities in Text-Attributed Graph (TAG) understanding.<n>We argue that graphs inherently contain rich structural and semantic information, and that their effective exploitation can unlock potential gains in LLMs reasoning performance.<n>We propose Homophily-aware Structural and Semantic Compression for LLMs (HS2C), a framework centered on exploiting graph homophily.
  arXiv  Detail & Related papers  (2026-01-13T03:35:18Z)
• Disco-RAG: Discourse-Aware Retrieval-Augmented Generation [81.53888908988756]
  We propose Disco-RAG, a discourse-aware framework that injects discourse signals into the generation process.<n>Our method constructs intra-chunk discourse trees to capture local hierarchies and builds inter-chunk rhetorical graphs to model cross-passage coherence.<n>Experiments on question answering and long-document summarization benchmarks show the efficacy of our approach.
  arXiv  Detail & Related papers  (2026-01-07T20:32:50Z)
• Cog-RAG: Cognitive-Inspired Dual-Hypergraph with Theme Alignment Retrieval-Augmented Generation [43.737415090081555]
  We propose a theme-aligned dual-hypergraph RAG framework (Cog-RAG) that uses a theme hypergraph to capture inter-chunk thematic structure and an entity hypergraph to model high-order semantic relations.<n>Our experiments demonstrate that Cog-RAG significantly outperforms existing state-of-the-art baseline approaches.
  arXiv  Detail & Related papers  (2025-11-17T10:10:33Z)
• TagRAG: Tag-guided Hierarchical Knowledge Graph Retrieval-Augmented Generation [20.741721911329048]
  Retrieval-Augmented Generation enhances language models by retrieving external knowledge to support informed and grounded responses.<n>Traditional RAG methods rely on fragment-level retrieval, limiting their ability to address query-focused summarization queries.<n>We propose TagRAG, a tag-guided hierarchical knowledge graph RAG framework for efficient global reasoning and scalable graph maintenance.
  arXiv  Detail & Related papers  (2025-10-18T08:24:49Z)
• IAR2: Improving Autoregressive Visual Generation with Semantic-Detail Associated Token Prediction [77.06211178777939]
  IAR2 is an advanced autoregressive framework that enables a hierarchical semantic-detail synthesis process.<n>We show that IAR2 sets a new state-of-the-art for autoregressive image generation, achieving a FID of 1.50 on ImageNet.
  arXiv  Detail & Related papers  (2025-10-08T12:08:21Z)
• Youtu-GraphRAG: Vertically Unified Agents for Graph Retrieval-Augmented Complex Reasoning [32.78218766121055]
  Graph retrieval-augmented generation (GraphRAG) has effectively enhanced large language models in complex reasoning.<n>We propose a vertically unified agentic paradigm, Youtu-GraphRAG, to jointly connect the entire framework as an intricate integration.
  arXiv  Detail & Related papers  (2025-08-27T13:13:20Z)
• LeanRAG: Knowledge-Graph-Based Generation with Semantic Aggregation and Hierarchical Retrieval [10.566901995776025]
  LeanRAG is a framework that combines knowledge aggregation and retrieval strategies.<n>It can mitigate the substantial overhead associated with path retrieval on graphs and minimizes redundant information retrieval.
  arXiv  Detail & Related papers  (2025-08-14T06:47:18Z)
• Beyond Chunking: Discourse-Aware Hierarchical Retrieval for Long Document Question Answering [51.7493726399073]
  We present a discourse-aware hierarchical framework to enhance long document question answering.<n>The framework involves three key innovations: specialized discourse parsing for lengthy documents, LLM-based enhancement of discourse relation nodes, and structure-guided hierarchical retrieval.
  arXiv  Detail & Related papers  (2025-05-26T14:45:12Z)
• RGL: A Graph-Centric, Modular Framework for Efficient Retrieval-Augmented Generation on Graphs [58.10503898336799]
  We introduce the RAG-on-Graphs Library (RGL), a modular framework that seamlessly integrates the complete RAG pipeline.<n>RGL addresses key challenges by supporting a variety of graph formats and integrating optimized implementations for essential components.<n>Our evaluations demonstrate that RGL not only accelerates the prototyping process but also enhances the performance and applicability of graph-based RAG systems.
  arXiv  Detail & Related papers  (2025-03-25T03:21:48Z)
• Refinement Module based on Parse Graph for Human Pose Estimation [9.106514619168536]
  We propose a new context relation and hierarchical structure modeling module, RMPG, based on Parse Graph.<n> RMPG adaptively refines feature maps through top-down decomposition of feature maps and bottom-up composition of sub-node feature maps with context information.<n>It can be flexibly embedded as a plug-in into various mainstream Human Pose Estimation networks.
  arXiv  Detail & Related papers  (2025-01-19T15:05:15Z)
• A Pure Transformer Pretraining Framework on Text-attributed Graphs [50.833130854272774]
  We introduce a feature-centric pretraining perspective by treating graph structure as a prior. Our framework, Graph Sequence Pretraining with Transformer (GSPT), samples node contexts through random walks. GSPT can be easily adapted to both node classification and link prediction, demonstrating promising empirical success on various datasets.
  arXiv  Detail & Related papers  (2024-06-19T22:30:08Z)
• SE-GSL: A General and Effective Graph Structure Learning Framework through Structural Entropy Optimization [67.28453445927825]
  Graph Neural Networks (GNNs) are de facto solutions to structural data learning. Existing graph structure learning (GSL) frameworks still lack robustness and interpretability. This paper proposes a general GSL framework, SE-GSL, through structural entropy and the graph hierarchy abstracted in the encoding tree.
  arXiv  Detail & Related papers  (2023-03-17T05:20:24Z)
• Dual-constrained Deep Semi-Supervised Coupled Factorization Network with Enriched Prior [80.5637175255349]
  We propose a new enriched prior based Dual-constrained Deep Semi-Supervised Coupled Factorization Network, called DS2CF-Net. To ex-tract hidden deep features, DS2CF-Net is modeled as a deep-structure and geometrical structure-constrained neural network. Our network can obtain state-of-the-art performance for representation learning and clustering.
  arXiv  Detail & Related papers  (2020-09-08T13:10:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.