RT Journal Article
T1 On the assessment of generative AI in modeling tasks: an experience report with ChatGPT and UML
A1 Cámara-Moreno, Javier
A1 Troya-Castilla, Javier
A1 Burgueño-Caballero, Lola
A1 Vallecillo-Moreno, Antonio Jesús
K1 Inteligencia artificial
K1 UML (Lenguaje de programación)
AB Most experts agree that large language models (LLMs), such as those used by Copilot and ChatGPT, are expected to revo-lutionize the way in which software is developed. Many papers are currently devoted to analyzing the potential advantagesand limitations of these generative AI models for writing code. However, the analysis of the current state of LLMs withrespect to software modeling has received little attention. In this paper, we investigate the current capabilities of ChatGPT toperform modeling tasks and to assist modelers, while also trying to identify its main shortcomings. Our findings show that,in contrast to code generation, the performance of the current version of ChatGPT for software modeling is limited, withvarious syntactic and semantic deficiencies, lack of consistency in responses and scalability issues. We also outline our viewson how we perceive the role that LLMs can play in the software modeling discipline in the short term, and how the modelingcommunity can help to improve the current capabilities of ChatGPT and the coming LLMs for software modeling.
PB Springer
YR 2023
FD 2023
LK https://hdl.handle.net/10630/26825
UL https://hdl.handle.net/10630/26825
LA eng
NO Cámara, J., Troya, J., Burgueño, L. et al. On the assessment of generative AI in modeling tasks: an experience report with ChatGPT and UML. Softw Syst Model 22, 781–793 (2023). https://doi.org/10.1007/s10270-023-01105-5
NO Funding for open access publishing: Universidad de Málaga/ CBUA
DS RIUMA. Repositorio Institucional de la Universidad de Málaga
RD 12 abr 2026