Human-Large Language Model collaboration for systematic ontology updates: a case study in the domain of dietary lifestyle.

Abstract

To develop and evaluate a human-LLM (Large Language Model) collaborative approach for systematic ontology updating, demonstrated with the Dietary Lifestyle Ontology (DILON). One hundred dietary questionnaire items from English and Korean sources were semantically annotated by 4 state-of-the-art language models, which generated candidate concepts for inclusion into DILON. Outputs were refined through cross-model reconciliation, followed by expert review. The model curated the concept within DILON and experts reviewed and refined the outputs in Protégé to ensure accuracy and consistency. Claude Sonnet 4 effectively supported local tasks, including harvesting new concepts, detecting redundancies, and refining hierarchical segments. Global optimization of ontology, however, required systematic examination by human experts. These findings highlight the complementary strengths of LLMs and humans: LLMs accelerate repetitive and local updates, whereas humans maintain overall structural integrity. Human-LLM collaboration improves efficiency, scalability, and sustainability in ontology engineering, supporting the maintenance of complex biomedical ontologies.