用大模型与知识图谱协同构建可持续发展目标知识图谱
LEC-KG: An LLM-Embedding Collaborative Framework for Domain-Specific Knowledge Graph Construction -- A Case Study on SDGs
- 大模型与嵌入模型双向协作，提升实体关系抽取精度
- 在低频关系上比纯大模型提升显著，准确率更高
- 适合政策文本结构化、可持续发展领域研究者使用
从非结构化文本构建特定领域知识图谱仍面临实体表述多样、长尾关系分布及缺乏标准模式等挑战。本文提出 LEC-KG，一种大语言模型（LLM）与知识图谱嵌入（KGE）双向协同框架。其核心包括：(1) 分层粗到细的关系抽取，缓解长尾偏差；(2) 基于证据的思维链反馈，使结构建议可追溯至原文；(3) 语义初始化，支持对未见实体的结构验证。两个模块通过迭代增强：KGE 提供结构感知反馈优化 LLM 抽取，而验证后的三元组逐步改进 KGE 表示。我们在中文可持续发展目标（SDG）报告上评估该框架，结果表明在低频关系上显著优于纯大模型基线。经多轮迭代，系统能可靠地将政策文本转化为可信的知识图谱三元组。
原文摘要 · Abstract (English)
Constructing domain-specific knowledge graphs from unstructured text remains challenging due to heterogeneous entity mentions, long-tail relation distributions, and the absence of standardized schemas. We present LEC-KG, a bidirectional collaborative framework that integrates the semantic understanding of Large Language Models (LLMs) with the structural reasoning of Knowledge Graph Embeddings (KGE). Our approach features three key components: (1) hierarchical coarse-to-fine relation extraction that mitigates long-tail bias, (2) evidence-guided Chain-of-Thought feedback that grounds structural suggestions in source text, and (3) semantic initialization that enables structural validation for unseen entities. The two modules enhance each other iteratively-KGE provides structure-aware feedback to refine LLM extractions, while validated triples progressively improve KGE representations. We evaluate LEC-KG on Chinese Sustainable Development Goal (SDG) reports, demonstrating substantial improvements over LLM baselines, particularly on low-frequency relations. Through iterative refinement, our framework reliably transforms unstructured policy text into validated knowledge graph triples.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。