Ontology Generation using Large Language Models
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912264441823232 |
|---|---|
| author | Lippolis, Anna Sofia Saeedizade, Mohammad Javad Keskisärkkä, Robin Zuppiroli, Sara Ceriani, Miguel Gangemi, Aldo Blomqvist, Eva Nuzzolese, Andrea Giovanni |
| author_facet | Lippolis, Anna Sofia Saeedizade, Mohammad Javad Keskisärkkä, Robin Zuppiroli, Sara Ceriani, Miguel Gangemi, Aldo Blomqvist, Eva Nuzzolese, Andrea Giovanni |
| contents | The ontology engineering process is complex, time-consuming, and error-prone, even for experienced ontology engineers. In this work, we investigate the potential of Large Language Models (LLMs) to provide effective OWL ontology drafts directly from ontological requirements described using user stories and competency questions. Our main contribution is the presentation and evaluation of two new prompting techniques for automated ontology development: Memoryless CQbyCQ and Ontogenia. We also emphasize the importance of three structural criteria for ontology assessment, alongside expert qualitative evaluation, highlighting the need for a multi-dimensional evaluation in order to capture the quality and usability of the generated ontologies. Our experiments, conducted on a benchmark dataset of ten ontologies with 100 distinct CQs and 29 different user stories, compare the performance of three LLMs using the two prompting techniques. The results demonstrate improvements over the current state-of-the-art in LLM-supported ontology engineering. More specifically, the model OpenAI o1-preview with Ontogenia produces ontologies of sufficient quality to meet the requirements of ontology engineers, significantly outperforming novice ontology engineers in modelling ability. However, we still note some common mistakes and variability of result quality, which is important to take into account when using LLMs for ontology authoring support. We discuss these limitations and propose directions for future research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_05388 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Ontology Generation using Large Language Models Lippolis, Anna Sofia Saeedizade, Mohammad Javad Keskisärkkä, Robin Zuppiroli, Sara Ceriani, Miguel Gangemi, Aldo Blomqvist, Eva Nuzzolese, Andrea Giovanni Artificial Intelligence The ontology engineering process is complex, time-consuming, and error-prone, even for experienced ontology engineers. In this work, we investigate the potential of Large Language Models (LLMs) to provide effective OWL ontology drafts directly from ontological requirements described using user stories and competency questions. Our main contribution is the presentation and evaluation of two new prompting techniques for automated ontology development: Memoryless CQbyCQ and Ontogenia. We also emphasize the importance of three structural criteria for ontology assessment, alongside expert qualitative evaluation, highlighting the need for a multi-dimensional evaluation in order to capture the quality and usability of the generated ontologies. Our experiments, conducted on a benchmark dataset of ten ontologies with 100 distinct CQs and 29 different user stories, compare the performance of three LLMs using the two prompting techniques. The results demonstrate improvements over the current state-of-the-art in LLM-supported ontology engineering. More specifically, the model OpenAI o1-preview with Ontogenia produces ontologies of sufficient quality to meet the requirements of ontology engineers, significantly outperforming novice ontology engineers in modelling ability. However, we still note some common mistakes and variability of result quality, which is important to take into account when using LLMs for ontology authoring support. We discuss these limitations and propose directions for future research. |
| title | Ontology Generation using Large Language Models |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2503.05388 |