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...
| Main Authors: | , , , |
|---|---|
| Format: | Conference item |
| Language: | English |
| Published: |
CEUR Workshop Proceedings
2023
|
| _version_ | 1817931249087414272 |
|---|---|
| author | He, Y Chen, J Dong, H Horrocks, I |
| author_facet | He, Y Chen, J Dong, H Horrocks, I |
| author_sort | He, Y |
| collection | OXFORD |
| description | 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. |
| first_indexed | 2024-12-09T03:19:01Z |
| format | Conference item |
| id | oxford-uuid:b0ecf14b-e9b9-4767-9fae-8a7adddd6fb6 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-12-09T03:19:01Z |
| publishDate | 2023 |
| publisher | CEUR Workshop Proceedings |
| record_format | dspace |
| spelling | oxford-uuid:b0ecf14b-e9b9-4767-9fae-8a7adddd6fb62024-11-05T11:27:47ZExploring large language models for ontology alignmentConference itemhttp://purl.org/coar/resource_type/c_5794uuid:b0ecf14b-e9b9-4767-9fae-8a7adddd6fb6EnglishSymplectic ElementsCEUR Workshop Proceedings2023He, YChen, JDong, HHorrocks, IThis 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. |
| spellingShingle | He, Y Chen, J Dong, H Horrocks, I Exploring large language models for ontology alignment |
| title | Exploring large language models for ontology alignment |
| title_full | Exploring large language models for ontology alignment |
| title_fullStr | Exploring large language models for ontology alignment |
| title_full_unstemmed | Exploring large language models for ontology alignment |
| title_short | Exploring large language models for ontology alignment |
| title_sort | exploring large language models for ontology alignment |
| work_keys_str_mv | AT hey exploringlargelanguagemodelsforontologyalignment AT chenj exploringlargelanguagemodelsforontologyalignment AT dongh exploringlargelanguagemodelsforontologyalignment AT horrocksi exploringlargelanguagemodelsforontologyalignment |