Investigating Open Source LLMs to Retrofit Competency Questions in Ontology Engineering
Proceedings of the AAAI Symposium Series · 08.11.2024 · 4 (1) · 188-198
DOI: 10.1609/aaaiss.v4i1.31793 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Symposium Series, online erschienen am 08.11.2024. Verfasst von Reham Alharbi und 3 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref).
Abstract (Originalsprache)
Competency Questions (CQs) are essential in ontology engineering; they express an ontology's functional requirements as natural language questions, offer crucial insights into an ontology's scope and are pivotal for various tasks, e.g. ontology reuse, testing, requirement specification, and pattern definition. Despite their importance, the practice of publishing CQs alongside ontological artefacts is not commonly adopted. We propose an approach based on Generative AI, specifically Large Language Models (LLMs) for retrofitting CQs from existing ontologies and we investigate how open LLMs (i.e. Llama-2-70b, Mistral 7B and Flan-T5-xl) perform in generating CQs for existing ontologies. We compare these results with our previous efforts using closed-source LLMs and we reflect on the results.
Zitieren
APA
Alharbi, R., Tamma, V., Grasso, F., & Payne, T. R. (2024). Investigating Open Source LLMs to Retrofit Competency Questions in Ontology Engineering. Proceedings of the AAAI Symposium Series, 4(1), 188-198. https://doi.org/10.1609/aaaiss.v4i1.31793
Vancouver
Alharbi R, Tamma V, Grasso F, Payne TR. Investigating Open Source LLMs to Retrofit Competency Questions in Ontology Engineering. Proceedings of the AAAI Symposium Series. 2024;4(1):188-198. doi:10.1609/aaaiss.v4i1.31793
BibTeX
@article{Alharbi2024,
author = {Alharbi, Reham and Tamma, Valentina and Grasso, Floriana and Payne, Terry R.},
title = {Investigating Open Source LLMs to Retrofit Competency Questions in Ontology Engineering},
journal = {Proceedings of the AAAI Symposium Series},
year = {2024},
volume = {4},
number = {1},
pages = {188--198},
doi = {10.1609/aaaiss.v4i1.31793}
}
EUVIMED