Ontology-Enhanced Knowledge Graph Completion using Large Language Models

TL;DR

This paper introduces OL-KGC, a novel method that combines neural perceptual embedding and ontological knowledge extraction to enhance knowledge graph completion with large language models, achieving state-of-the-art results.

Contribution

It presents an ontology-enhanced KGC approach that integrates structural and ontological information into LLMs, improving reasoning and accuracy.

Findings

OL-KGC outperforms existing methods on benchmark datasets.

The approach achieves state-of-the-art performance across multiple metrics.

Incorporating ontological knowledge improves reasoning capabilities.

Abstract

Large Language Models (LLMs) have been extensively adopted in Knowledge Graph Completion (KGC), showcasing significant research advancements. However, as black-box models driven by deep neural architectures, current LLM-based KGC methods rely on implicit knowledge representation with parallel propagation of erroneous knowledge, thereby hindering their ability to produce conclusive and decisive reasoning outcomes. We aim to integrate neural-perceptual structural information with ontological knowledge, leveraging the powerful capabilities of LLMs to achieve a deeper understanding of the intrinsic logic of the knowledge. We propose an ontology enhanced KGC method using LLMs -- OL-KGC. It first leverages neural perceptual mechanisms to effectively embed structural information into the textual space, and then uses an automated extraction algorithm to retrieve ontological knowledge from the knowledge graphs (KGs) that needs to be completed, which is further transformed into a textual format comprehensible to LLMs for providing logic guidance. We conducted extensive experiments on three widely-used benchmarks -- FB15K-237, UMLS and WN18RR. The experimental results demonstrate that OL-KGC significantly outperforms existing mainstream KGC methods across multiple evaluation metrics, achieving state-of-the-art performance.