Exploring large language models for ontology alignment

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-shot1 performance of Flan-T5-XXL and GPT-3.5-turbo, we leverage chall...

Mô tả đầy đủ

Chi tiết về thư mục
Những tác giả chính: He, Y, Chen, J, Dong, H, Horrocks, I
Định dạng: Conference item
Ngôn ngữ:English
Được phát hành: CEUR Workshop Proceedings 2023
Miêu tả
Tóm tắt: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-shot1 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.