LKD-KGC: Domain-Specific KG Construction via LLM-driven Knowledge Dependency Parsing

TL;DR

This paper introduces LKD-KGC, an unsupervised framework that leverages large language models to construct high-quality domain-specific knowledge graphs by analyzing document dependencies and generating entity schemas without predefined structures.

Contribution

The paper presents a novel unsupervised approach for domain-specific knowledge graph construction that overcomes limitations of schema reliance and single-document processing in existing methods.

Findings

Achieves 10-20% improvements in precision and recall over baselines.

Effectively infers knowledge dependencies and entity schemas from document repositories.

Demonstrates high-quality KG construction in complex domain-specific corpora.

Abstract

Knowledge Graphs (KGs) structure real-world entities and their relationships into triples, enhancing machine reasoning for various tasks. While domain-specific KGs offer substantial benefits, their manual construction is often inefficient and requires specialized knowledge. Recent approaches for knowledge graph construction (KGC) based on large language models (LLMs), such as schema-guided KGC and reference knowledge integration, have proven efficient. However, these methods are constrained by their reliance on manually defined schema, single-document processing, and public-domain references, making them less effective for domain-specific corpora that exhibit complex knowledge dependencies and specificity, as well as limited reference knowledge. To address these challenges, we propose LKD-KGC, a novel framework for unsupervised domain-specific KG construction. LKD-KGC autonomously analyzes document repositories to infer knowledge dependencies, determines optimal processing sequences via LLM driven prioritization, and autoregressively generates entity schema by integrating hierarchical inter-document contexts. This schema guides the unsupervised extraction of entities and relationships, eliminating reliance on predefined structures or external knowledge. Extensive experiments show that compared with state-of-the-art baselines, LKD-KGC generally achieves improvements of 10% to 20% in both precision and recall rate, demonstrating its potential in constructing high-quality domain-specific KGs.