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

2025-05-30

AI Summary

Manual construction of domain-specific knowledge graphs (KGs) is inefficient, while existing large language model (LLM)-based approaches rely heavily on handcrafted schemas and external knowledge sources, limiting their ability to handle complex inter-entity dependencies and sparse reference information. Method: We propose LKD-KGC, an unsupervised framework featuring a novel knowledge-dependency-aware, LLM-driven mechanism. It autonomously parses implicit knowledge structures from document corpora, dynamically generates hierarchical entity schemas, and guides cross-document triplet extraction—without requiring predefined schemas or external knowledge. The approach integrates LLM-based reasoning, knowledge-dependency graph construction, autoregressive schema generation, and unsupervised relation extraction. Contribution/Results: On multiple domain-specific benchmarks, LKD-KGC achieves 10–20% improvements in both precision and recall over state-of-the-art methods, significantly enhancing KG construction quality, robustness, and generalizability.

Technology Category

• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Knowledge Representation and Reasoning: Description Logics
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

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.

Problem

• Constructs domain-specific KGs without manual schemas
• Handles complex knowledge dependencies in specialized corpora
• Autonomously infers knowledge from document repositories

Innovation

• Autonomous knowledge dependency parsing via LLM
• Hierarchical inter-document schema generation
• Unsupervised entity-relation extraction without predefined structures