HyperGraphRAG: Retrieval-Augmented Generation via Hypergraph-Structured Knowledge Representation
This addresses a bottleneck in retrieval-augmented generation for AI applications by enabling better representation of complex real-world knowledge, though it is an incremental improvement over existing graph-based approaches.
The paper tackles the limitation of existing graph-based RAG methods, which use binary relations, by proposing HyperGraphRAG, a hypergraph-based method that represents n-ary relations to improve knowledge representation. Experiments across multiple domains show it outperforms standard and previous graph-based RAG methods in accuracy, efficiency, and generation quality.
Standard Retrieval-Augmented Generation (RAG) relies on chunk-based retrieval, whereas GraphRAG advances this approach by graph-based knowledge representation. However, existing graph-based RAG approaches are constrained by binary relations, as each edge in an ordinary graph connects only two entities, limiting their ability to represent the n-ary relations (n >= 2) in real-world knowledge. In this work, we propose HyperGraphRAG, a novel hypergraph-based RAG method that represents n-ary relational facts via hyperedges, and consists of knowledge hypergraph construction, retrieval, and generation. Experiments across medicine, agriculture, computer science, and law demonstrate that HyperGraphRAG outperforms both standard RAG and previous graph-based RAG methods in answer accuracy, retrieval efficiency, and generation quality. Our data and code are publicly available at https://github.com/LHRLAB/HyperGraphRAG.