HyperbolicRAG: Enhancing Retrieval-Augmented Generation with Hyperbolic Representations

• URL: http://arxiv.org/abs/2511.18808v2
• Date: Tue, 25 Nov 2025 03:43:52 GMT
• Title: HyperbolicRAG: Enhancing Retrieval-Augmented Generation with Hyperbolic Representations
• Authors: Linxiao Cao, Ruitao Wang, Jindong Li, Zhipeng Zhou, Menglin Yang,
• Abstract summary: Graph-based RAG enables large language models to access external knowledge.<n>We propose HyperbolicRAG, a retrieval framework that integrates hyperbolic geometry into graph-based RAG.
• Score: 11.678218711095269
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Retrieval-augmented generation (RAG) enables large language models (LLMs) to access external knowledge, helping mitigate hallucinations and enhance domain-specific expertise. Graph-based RAG enhances structural reasoning by introducing explicit relational organization that enables information propagation across semantically connected text units. However, these methods typically rely on Euclidean embeddings that capture semantic similarity but lack a geometric notion of hierarchical depth, limiting their ability to represent abstraction relationships inherent in complex knowledge graphs. To capture both fine-grained semantics and global hierarchy, we propose HyperbolicRAG, a retrieval framework that integrates hyperbolic geometry into graph-based RAG. HyperbolicRAG introduces three key designs: (1) a depth-aware representation learner that embeds nodes within a shared Poincare manifold to align semantic similarity with hierarchical containment, (2) an unsupervised contrastive regularization that enforces geometric consistency across abstraction levels, and (3) a mutual-ranking fusion mechanism that jointly exploits retrieval signals from Euclidean and hyperbolic spaces, emphasizing cross-space agreement during inference. Extensive experiments across multiple QA benchmarks demonstrate that HyperbolicRAG outperforms competitive baselines, including both standard RAG and graph-augmented baselines.

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)
• HypRAG: Hyperbolic Dense Retrieval for Retrieval Augmented Generation [30.711145880382286]
  HyTE-FH and HyTE-H are hyperbolic representations projecting pre-trained Euclidean embeddings into hyperbolic space.<n>The Outward Einstein Midpoint is a geometry-aware pooling operator that provably preserves hierarchical structure.<n>Our analysis also reveals that hyperbolic representations encode document specificity through norm-based separation.
  arXiv  Detail & Related papers  (2026-02-08T00:18:05Z)
• 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)
• H3Former: Hypergraph-based Semantic-Aware Aggregation via Hyperbolic Hierarchical Contrastive Loss for Fine-Grained Visual Classification [17.431440244641585]
  H3Former is a novel token-to-region framework for fine-grained visual classification.<n>SAAM exploits multi-scale contextual cues to dynamically construct a weighted hypergraph among tokens.<n>HHCL enforces hierarchical semantic constraints in a non-Euclidean embedding space.
  arXiv  Detail & Related papers  (2025-11-13T12:49:10Z)
• GeoGNN: Quantifying and Mitigating Semantic Drift in Text-Attributed Graphs [59.61242815508687]
  Graph neural networks (GNNs) on text--attributed graphs (TAGs) encode node texts using pretrained language models (PLMs) and propagate these embeddings through linear neighborhood aggregation.<n>This work introduces a local PCA-based metric that measures the degree of semantic drift and provides the first quantitative framework to analyze how different aggregation mechanisms affect manifold structure.
  arXiv  Detail & Related papers  (2025-11-12T06:48:43Z)
• Dense Semantic Matching with VGGT Prior [49.42199006453071]
  We propose an approach that retains VGGT's intrinsic strengths by reusing early feature stages, fine-tuning later ones, and adding a semantic head for bidirectional correspondences.<n>Our approach achieves superior geometry awareness, matching reliability, and manifold preservation, outperforming previous baselines.
  arXiv  Detail & Related papers  (2025-09-25T14:56:11Z)
• 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)
• Learning Efficient and Generalizable Graph Retriever for Knowledge-Graph Question Answering [75.12322966980003]
  Large Language Models (LLMs) have shown strong inductive reasoning ability across various domains.<n>Most existing RAG pipelines rely on unstructured text, limiting interpretability and structured reasoning.<n>Recent studies have explored integrating knowledge graphs with LLMs for knowledge graph question answering.<n>We propose RAPL, a novel framework for efficient and effective graph retrieval in KGQA.
  arXiv  Detail & Related papers  (2025-06-11T12:03:52Z)
• Robust Saliency-Aware Distillation for Few-shot Fine-grained Visual Recognition [57.08108545219043]
  Recognizing novel sub-categories with scarce samples is an essential and challenging research topic in computer vision. Existing literature addresses this challenge by employing local-based representation approaches. This article proposes a novel model, Robust Saliency-aware Distillation (RSaD), for few-shot fine-grained visual recognition.
  arXiv  Detail & Related papers  (2023-05-12T00:13:17Z)
• Geometry Contrastive Learning on Heterogeneous Graphs [50.58523799455101]
  This paper proposes a novel self-supervised learning method, termed as Geometry Contrastive Learning (GCL) GCL views a heterogeneous graph from Euclidean and hyperbolic perspective simultaneously, aiming to make a strong merger of the ability of modeling rich semantics and complex structures. Extensive experiments on four benchmarks data sets show that the proposed approach outperforms the strong baselines.
  arXiv  Detail & Related papers  (2022-06-25T03:54:53Z)
• Spatial-Spectral Clustering with Anchor Graph for Hyperspectral Image [88.60285937702304]
  This paper proposes a novel unsupervised approach called spatial-spectral clustering with anchor graph (SSCAG) for HSI data clustering. The proposed SSCAG is competitive against the state-of-the-art approaches.
  arXiv  Detail & Related papers  (2021-04-24T08:09:27Z)
• Interpretable Signed Link Prediction with Signed Infomax Hyperbolic Graph [54.03786611989613]
  signed link prediction in social networks aims to reveal the underlying relationships (i.e. links) among users (i.e. nodes) We develop a unified framework, termed as Signed Infomax Hyperbolic Graph (textbfSIHG) In order to model high-order user relations and complex hierarchies, the node embeddings are projected and measured in a hyperbolic space with a lower distortion.
  arXiv  Detail & Related papers  (2020-11-25T05:09:03Z)

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.