Hyper-KGGen: A Skill-Driven Knowledge Extractor for High-Quality Knowledge Hypergraph Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915812017700864 |
|---|---|
| author | Huang, Rizhuo Feng, Yifan Xue, Rundong Ying, Shihui Yong, Jun-Hai Shi, Chuan Du, Shaoyi Gao, Yue |
| author_facet | Huang, Rizhuo Feng, Yifan Xue, Rundong Ying, Shihui Yong, Jun-Hai Shi, Chuan Du, Shaoyi Gao, Yue |
| contents | Knowledge hypergraphs surpass traditional binary knowledge graphs by encapsulating complex $n$-ary atomic facts, providing a more comprehensive paradigm for semantic representation. However, constructing high-quality hypergraphs remains challenging due to the \textit{scenario gap}: generic extractors struggle to generalize across diverse domains with specific jargon, while existing methods often fail to balance structural skeletons with fine-grained details. To bridge this gap, we propose \textbf{Hyper-KGGen}, a skill-driven framework that reformulates extraction as a dynamic skill-evolving process. First, Hyper-KGGen employs a \textit{coarse-to-fine} mechanism to systematically decompose documents, ensuring full-dimensional coverage from binary links to complex hyperedges. Crucially, it incorporates an \textit{adaptive skill acquisition} module that actively distills domain expertise into a Global Skill Library. This is achieved via a stability-based feedback loop, where extraction stability serves as a relative reward signal to induce high-quality skills from unstable traces and missed predictions. Additionally, we present \textbf{HyperDocRED}, a rigorously annotated benchmark for document-level knowledge hypergraph extraction. Experiments demonstrate that Hyper-KGGen significantly outperforms strong baselines, validating that evolved skills provide substantially richer guidance than static few-shot examples in multi-scenario settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_19543 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Hyper-KGGen: A Skill-Driven Knowledge Extractor for High-Quality Knowledge Hypergraph Generation Huang, Rizhuo Feng, Yifan Xue, Rundong Ying, Shihui Yong, Jun-Hai Shi, Chuan Du, Shaoyi Gao, Yue Computation and Language Information Retrieval Knowledge hypergraphs surpass traditional binary knowledge graphs by encapsulating complex $n$-ary atomic facts, providing a more comprehensive paradigm for semantic representation. However, constructing high-quality hypergraphs remains challenging due to the \textit{scenario gap}: generic extractors struggle to generalize across diverse domains with specific jargon, while existing methods often fail to balance structural skeletons with fine-grained details. To bridge this gap, we propose \textbf{Hyper-KGGen}, a skill-driven framework that reformulates extraction as a dynamic skill-evolving process. First, Hyper-KGGen employs a \textit{coarse-to-fine} mechanism to systematically decompose documents, ensuring full-dimensional coverage from binary links to complex hyperedges. Crucially, it incorporates an \textit{adaptive skill acquisition} module that actively distills domain expertise into a Global Skill Library. This is achieved via a stability-based feedback loop, where extraction stability serves as a relative reward signal to induce high-quality skills from unstable traces and missed predictions. Additionally, we present \textbf{HyperDocRED}, a rigorously annotated benchmark for document-level knowledge hypergraph extraction. Experiments demonstrate that Hyper-KGGen significantly outperforms strong baselines, validating that evolved skills provide substantially richer guidance than static few-shot examples in multi-scenario settings. |
| title | Hyper-KGGen: A Skill-Driven Knowledge Extractor for High-Quality Knowledge Hypergraph Generation |
| topic | Computation and Language Information Retrieval |
| url | https://arxiv.org/abs/2602.19543 |