Saved in:
Bibliographic Details
Main Authors: Zeng, Yikai, Piao, Yingchao, Pei, Changhua, Li, Jianhui
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.02090
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911472708222976
author Zeng, Yikai
Piao, Yingchao
Pei, Changhua
Li, Jianhui
author_facet Zeng, Yikai
Piao, Yingchao
Pei, Changhua
Li, Jianhui
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_02090
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle LEC-KG: An LLM-Embedding Collaborative Framework for Domain-Specific Knowledge Graph Construction -- A Case Study on SDGs
Zeng, Yikai
Piao, Yingchao
Pei, Changhua
Li, Jianhui
Computation and Language
Artificial Intelligence
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.
title LEC-KG: An LLM-Embedding Collaborative Framework for Domain-Specific Knowledge Graph Construction -- A Case Study on SDGs
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2602.02090