LLMs4OM: Matching Ontologies with Large Language Models

TL;DR

The paper introduces LLMs4OM, a framework leveraging large language models for ontology matching, demonstrating their effectiveness and potential to outperform traditional systems across diverse datasets.

Contribution

It presents a novel framework that evaluates LLMs in ontology matching tasks using zero-shot prompting, showing their competitive performance in complex scenarios.

Findings

LLMs can match and surpass traditional OM systems in various datasets.

Zero-shot prompting enhances LLMs' effectiveness in ontology matching.

The framework demonstrates LLMs' potential in knowledge integration tasks.

Abstract

Ontology Matching (OM), is a critical task in knowledge integration, where aligning heterogeneous ontologies facilitates data interoperability and knowledge sharing. Traditional OM systems often rely on expert knowledge or predictive models, with limited exploration of the potential of Large Language Models (LLMs). We present the LLMs4OM framework, a novel approach to evaluate the effectiveness of LLMs in OM tasks. This framework utilizes two modules for retrieval and matching, respectively, enhanced by zero-shot prompting across three ontology representations: concept, concept-parent, and concept-children. Through comprehensive evaluations using 20 OM datasets from various domains, we demonstrate that LLMs, under the LLMs4OM framework, can match and even surpass the performance of traditional OM systems, particularly in complex matching scenarios. Our results highlight the potential of LLMs to significantly contribute to the field of OM.