Publikationen:

• Maier, Pierre; Kadziolka, Vicky: A Proposal for More Realistic Case Descriptions in Modeling Exercises. In: ACM/IEEE 29th International Conference on Model Driven Engineering Languages and Systems (MODELS Companion 2026), October 04--09, 2026, Málaga, Spain. 2026. doi:10.1145/3837062.3838916KurzfassungPDF Details BIB Download

  Modeling education relies on modeling exercises that are constituted by case descriptions. Many case descriptions explicitly state all required abstractions, reducing modeling activity largely to the translation of a natural-language text into the constructs of a modeling language. This paper proposes a set of five guidelines, abbreviated by the acronym L.I.C.I.A., for formulating more realistic case descriptions that expose students to modeling decisions more commonly encountered in practice. We apply the guidelines for formulating an example case description tailored to modeling a UML class diagram. Our first experiences with this case description suggest that case descriptions following the L.I.C.I.A. guidelines confront students with additional modeling decisions, such as choosing the data type of an attribute based on example values. Future work should investigate the guidelines for case descriptions in various kinds of modeling exercises and conduct a more comprehensive evaluation of using case descriptions following the guidelines in different teaching contexts. 

• Maier, Pierre; Kadziolka, Vicky: Model Deepening with Large Language Models: Insights from Exploratory Studies with ChatGPT. In: Bernasconi, Anna; Fonseca, Claudenir M.; de Cesare, Sergio; Bellatreche, Ladjel; Pastor, Oscar (Hrsg.): Advances in Conceptual Modeling: ER 2025 Workshops, CMLS, FCM, LLM4Modeling, OntoCom, and QUAMES, Poitiers, France, October 20–23, 2025, Proceedings. 2026. doi:10.1007/978-3-032-08620-4_8Kurzfassung Details BIB Download

  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.