DaSeLab at LLMs4OL 2024 Task A: Towards Term Typing in Ontology Learning
The report presents the evaluation results of our approach in the LLM4OL Challenge, where we fine-tuned GPT-3.5 for Task A (Term Typing) across three different datasets. Our approach demonstrated consistent and robust performance during few- shot testing, achieving top rankings in several datasets and sub-datasets, proving the potential of fine-tuning LLMs for ontology creation tasks.
Authors
- Pascal Hitzler (ORCID: https://orcid.org/0000-0001-6192-3472)
- Sanaz Saki Norouzi
- Adrita Barua (ORCID: https://orcid.org/0000-0002-3287-7443)
Institutions
- Kansas State University (US)
Publication Details
- Journal
- Open Conference Proceedings
- Published
- 2024-10-02
- DOI
- https://doi.org/10.52825/ocp.v4i.2489
- Citations
- 3
- Primary Topic
- Natural Language Processing Techniques
- Type
- article
- Field-Weighted Citation Impact
- 0.45
Funders
- National Science Foundation