Art der Publikation: Beitrag in Sammelwerk

Model Deepening with Large Language Models: Insights from Exploratory Studies with ChatGPT

Autor(en):

Maier, Pierre; Kadziolka, Vicky

Herausgeber:

Bernasconi, Anna; Fonseca, Claudenir M.; de Cesare, Sergio; Bellatreche, Ladjel; Pastor, Oscar

Titel des Sammelbands:

Advances in Conceptual Modeling: ER 2025 Workshops, CMLS, FCM, LLM4Modeling, OntoCom, and QUAMES, Poitiers, France, October 20–23, 2025, Proceedings

Veröffentlichung:

2026

Digital Object Identifier (DOI):

doi:10.1007/978-3-032-08620-4_8

Zitation:

Download BibTeX

Kurzfassung

Although multi-level modeling has long been argued to showcase benefits in various application domains, its adoption is still hindered not least because the construction of multi-level models may entail a cumbersome and error-prone re-engineering effort. While many studies have investigated the potential of using LLMs to support the automatic construction of two-level conceptual models, such as UML class diagrams, no research has yet been conducted on using LLMs to support the construction of multi-level conceptual models. In this paper, we report on experiments conducted with ChatGPT to support the re-engineering of flat two-level models into deep multi-level models – a process we refer to as model deepening – using the multi-level modeling language FMML. Our findings indicate that while ChatGPT can significantly aid in semantic tasks during model deepening – such as comparing attribute meanings or analyzing type-object patterns – it also presents challenges, sometimes generating erroneous models by removing and duplicating properties. Future research should aim to develop an overarching model-deepening method that integrates probabilistic information sources, such as ChatGPT, with rule-based algorithms, while clearly defining and leveraging the user’s role in guiding and validating the process.