Conceptual Modeling and Large Language Models: Impressions From First Experiments With ChatGPT
BP2-STS
- Fill, Hans-Georg ORCID University of Fribourg
- Fettke, Peter ORCID Saarland University and German Research Center for Artificial Intelligence (DFKI)
- Köpke, Julius ORCID University of Klagenfurt
- 06.04.2023
Published in:
- Enterprise Modelling and Information Systems Architectures (EMISAJ). - Enterprise Modelling and Information Systems Architectures (EMISAJ). - 2023, vol. 18, no. 3, p. 1-15
English
We will describe in the following several experiments we have conducted using ChatGPT based on the most recent GPT-4 models to explore which potential applications can be imagined in the future for generating and interpreting conceptual models. Thereby, we explore how to generate and interpret ER, Business Process, and UML class diagrams as well as Heraklit models. Our goal is to highlight how modeling applications based on large language models such as ChatGPT could be realized. We do not claim a full coverage of all functionalities, but rather aim to inspire the community to build on our examples and propose their own approaches.
- Faculty
- Faculté des sciences économiques et sociales et du management
- Department
- Département d'informatique
- Language
-
- English
- Classification
- Computer science and technology
- License
- License undefined
- Open access status
- green
- Identifiers
- Persistent URL
- https://folia.unifr.ch/unifr/documents/324646
Statistics
Document views: 913
File downloads:
- 318.pdf: 618