GenOM: ontology matching with description generation and large language models

Yiping Song, Jiaoyan Chen, Renate A. Schmidt

Abstract: Ontology matching (OM) plays an essential role in enabling semantic interoperability and integration across heterogeneous knowledge sources, particularly in biomedical domains which contain numerous complex concepts related to diseases and pharmaceuticals. This paper introduces GenOM, a large language model (LLM)-based ontology alignment framework, which enriches semantic representations of ontology concepts via generating textual definitions, retrieving alignment candidates with an embedding model, and incorporating exact lexical matching 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. Ablation studies confirm the effectiveness of semantic enrichment, highlighting the framework’s robustness and adaptability. Beyond the matching framework itself, this paper introduces a set of criteria for evaluating the quality of concept definitions that are generated, providing a more systematic basis for analysing LLM-generated descriptions.

External IDs:dblp:journals/www/SongCS26