Scholarlink

To address the challenges of traditional knowledge graph construction (KGC) methods, this paper proposes a framework AdaOntoKG that combines ontology-driven and adaptive chain-of-thought reasoning (Adaptive CoT). The framework builds and expands domain ontologies with LLMs, and guides triple extraction through Zero-Shot-CoT and Few-Shot-CoT, with ontology constraints ensuring semantic consistency and structural validity. Experiments on multiple benchmarks show that AdaOntoKG outperforms mainstream baselines in F1 and AUC, while achieving high ontology conformance. Overall, AdaOntoKG enhances accuracy, controllability, and domain adaptability, providing a scalable solution for constructing high-quality knowledge graphs.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Ontology-Guided Chain-of-Thought Reasoning for Knowledge Graph Construction with Large Language Model

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Gang Xiao,
  • Wenhui Li,
  • Jiawei Lu,
  • Siyu Chen

摘要

To address the challenges of traditional knowledge graph construction (KGC) methods, this paper proposes a framework AdaOntoKG that combines ontology-driven and adaptive chain-of-thought reasoning (Adaptive CoT). The framework builds and expands domain ontologies with LLMs, and guides triple extraction through Zero-Shot-CoT and Few-Shot-CoT, with ontology constraints ensuring semantic consistency and structural validity. Experiments on multiple benchmarks show that AdaOntoKG outperforms mainstream baselines in F1 and AUC, while achieving high ontology conformance. Overall, AdaOntoKG enhances accuracy, controllability, and domain adaptability, providing a scalable solution for constructing high-quality knowledge graphs.