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.
翻译:检索增强生成(RAG)使大型语言模型(LLM)能够访问外部知识,有助于缓解幻觉并增强领域特定专业知识。基于图的RAG通过引入显式关系组织来增强结构化推理,该组织支持信息在语义相连的文本单元间传播。然而,这些方法通常依赖于欧几里得嵌入,其虽能捕捉语义相似性,但缺乏层次深度的几何概念,限制了表示复杂知识图谱中固有抽象关系的能力。为同时捕获细粒度语义和全局层次结构,我们提出HyperbolicRAG,一种将双曲几何集成到基于图的RAG中的检索框架。HyperbolicRAG引入了三个关键设计:(1)深度感知表示学习器,将节点嵌入共享的庞加莱流形中以对齐语义相似性与层次包含关系;(2)无监督对比正则化,强制不同抽象层级间的几何一致性;(3)互排序融合机制,联合利用来自欧几里得空间和双曲空间的检索信号,在推理过程中强调跨空间一致性。在多个问答基准上的广泛实验表明,HyperbolicRAG优于包括标准RAG和图增强基线在内的竞争性基线。