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

2026-02-23

AI Summary

Traditional knowledge graphs struggle to model complex n-ary relations, and existing extraction methods often fail to simultaneously capture structural skeletons and fine-grained details in cross-domain scenarios. To address this challenge, this work proposes Hyper-KGGen, a novel framework that introduces a skill-driven dynamic knowledge extraction paradigm. By leveraging a coarse-to-fine document decomposition mechanism and an adaptive skill acquisition module, the approach formulates hypergraph extraction as a skill evolution process, enhanced by stability feedback signals that distill high-quality domain-specific skills from unstable extraction traces. The study also releases HyperDocRED, a document-level knowledge hypergraph benchmark dataset. Experimental results demonstrate that the proposed method significantly outperforms strong baselines, confirming that evolved skills are more effective than static few-shot exemplars in enhancing both the completeness and accuracy of knowledge hypergraphs.

Technology Category

• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Knowledge Representation and Reasoning: Knowledge Acquisition
• Natural Language Processing: Information Extraction

Application Category

• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Models for Web evolution

Abstract

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.

Problem

• knowledge hypergraph
• scenario gap
• domain-specific extraction
• n-ary facts
• knowledge graph construction

Innovation

• skill-driven knowledge extraction
• knowledge hypergraph generation
• adaptive skill acquisition
• coarse-to-fine decomposition
• stability-based feedback