LLMs4OM: Matching Ontologies with Large Language Models
This addresses the critical task of aligning heterogeneous ontologies for data interoperability and knowledge sharing, representing an incremental advancement by applying LLMs to a domain previously reliant on expert knowledge or predictive models.
The paper tackled the problem of ontology matching by evaluating the effectiveness of Large Language Models (LLMs) through the LLMs4OM framework, demonstrating that LLMs can match or surpass traditional systems in performance across 20 datasets.
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.