Exploring Large Language Models for Ontology Alignment
This addresses ontology alignment for knowledge integration, but it is incremental as it applies existing LLMs to a known problem.
This work investigated using large language models (LLMs) like Flan-T5-XXL and GPT-3.5-turbo for ontology alignment to identify concept equivalence mappings, finding they have the potential to outperform existing systems such as BERTMap with careful framework and prompt design.
This work investigates the applicability of recent generative Large Language Models (LLMs), such as the GPT series and Flan-T5, to ontology alignment for identifying concept equivalence mappings across ontologies. To test the zero-shot performance of Flan-T5-XXL and GPT-3.5-turbo, we leverage challenging subsets from two equivalence matching datasets of the OAEI Bio-ML track, taking into account concept labels and structural contexts. Preliminary findings suggest that LLMs have the potential to outperform existing ontology alignment systems like BERTMap, given careful framework and prompt design.