GenOM: Ontology Matching with Description Generation and Large Language Model

TL;DR

GenOM is a novel LLM-based framework for ontology matching that enhances semantic representations with generated definitions, retrieves candidates via embeddings, and improves precision with exact matching, showing competitive results in biomedical ontology alignment.

Contribution

The paper introduces GenOM, a new LLM-based ontology matching framework that combines semantic enrichment, embedding retrieval, and exact matching to outperform existing methods.

Findings

GenOM achieves competitive performance on the OAEI Bio-ML benchmark.

Semantic enrichment and few-shot prompting significantly improve matching accuracy.

The framework demonstrates robustness and adaptability across different ontology pairs.

Abstract

Ontology matching (OM) plays an essential role in enabling semantic interoperability and integration across heterogeneous knowledge sources, particularly in the biomedical domain which contains numerous complex concepts related to diseases and pharmaceuticals. This paper introduces GenOM, a large language model (LLM)-based ontology alignment framework, which enriches the semantic representations of ontology concepts via generating textual definitions, retrieves alignment candidates with an embedding model, and incorporates exact matching-based tools to improve precision. Extensive experiments conducted on the OAEI Bio-ML track demonstrate that GenOM can often achieve competitive performance, surpassing many baselines including traditional OM systems and recent LLM-based methods. Further ablation studies confirm the effectiveness of semantic enrichment and few-shot prompting, highlighting the framework's robustness and adaptability.