HyperGraphRAG: Retrieval-Augmented Generation via Hypergraph-Structured Knowledge Representation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915564683788288 |
|---|---|
| author | Luo, Haoran E, Haihong Chen, Guanting Zheng, Yandan Wu, Xiaobao Guo, Yikai Lin, Qika Feng, Yu Kuang, Zemin Song, Meina Zhu, Yifan Tuan, Luu Anh |
| author_facet | Luo, Haoran E, Haihong Chen, Guanting Zheng, Yandan Wu, Xiaobao Guo, Yikai Lin, Qika Feng, Yu Kuang, Zemin Song, Meina Zhu, Yifan Tuan, Luu Anh |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_21322 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HyperGraphRAG: Retrieval-Augmented Generation via Hypergraph-Structured Knowledge Representation Luo, Haoran E, Haihong Chen, Guanting Zheng, Yandan Wu, Xiaobao Guo, Yikai Lin, Qika Feng, Yu Kuang, Zemin Song, Meina Zhu, Yifan Tuan, Luu Anh Artificial Intelligence 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. |
| title | HyperGraphRAG: Retrieval-Augmented Generation via Hypergraph-Structured Knowledge Representation |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2503.21322 |