Cross-Granularity Hypergraph Retrieval-Augmented Generation for Multi-hop Question Answering

TL;DR

This paper introduces HGRAG, a hypergraph-based retrieval method for multi-hop question answering that effectively combines structural and semantic information, leading to improved accuracy and efficiency.

Contribution

HGRAG is a novel cross-granularity retrieval approach that integrates structural hypergraphs with semantic similarity for enhanced multi-hop QA.

Findings

Outperforms state-of-the-art QA methods in accuracy.

Achieves 6× faster retrieval speed.

Effectively combines structural and semantic information.

Abstract

Multi-hop question answering (MHQA) requires integrating knowledge scattered across multiple passages to derive the correct answer. Traditional retrieval-augmented generation (RAG) methods primarily focus on coarse-grained textual semantic similarity and ignore structural associations among dispersed knowledge, which limits their effectiveness in MHQA tasks. GraphRAG methods address this by leveraging knowledge graphs (KGs) to capture structural associations, but they tend to overly rely on structural information and fine-grained word- or phrase-level retrieval, resulting in an underutilization of textual semantics. In this paper, we propose a novel RAG approach called HGRAG for MHQA that achieves cross-granularity integration of structural and semantic information via hypergraphs. Structurally, we construct an entity hypergraph where fine-grained entities serve as nodes and coarse-grained passages as hyperedges, and establish knowledge association through shared entities. Semantically, we design a hypergraph retrieval method that integrates fine-grained entity similarity and coarse-grained passage similarity via hypergraph diffusion. Finally, we employ a retrieval enhancement module, which further refines the retrieved results both semantically and structurally, to obtain the most relevant passages as context for answer generation with the LLM. Experimental results on benchmark datasets demonstrate that our approach outperforms state-of-the-art methods in QA performance, and achieves a 6$\times$ speedup in retrieval efficiency.