Hyper-KGGen: A Skill-Driven Knowledge Extractor for High-Quality Knowledge Hypergraph Generation

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 $\mathit{\text{scenario}}\mathit{\text{gap}}$: 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 $\mathbf{\text{Hyper-KGGen}}$, a skill-driven framework that reformulates extraction as a dynamic skill-evolving process. First, Hyper-KGGen employs a $\mathit{\text{coarse-to-fine}}$ mechanism to systematically decompose documents, ensuring full-dimensional coverage from binary links to complex hyperedges. Crucially, it incorporates an $\mathit{\text{adaptive}}\mathit{\text{skill}}\mathit{\text{acquisition}}$ 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 $\mathbf{\text{HyperDocRED}}$, 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.