Large Language Models for UML Class Diagram Modeling: A Preliminary Empirical Evaluation
Applied Sciences · 01.07.2026 · 16 (13) · 6540
DOI: 10.3390/app16136540 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 01.07.2026. Verfasst von Yong Cheng und 6 weiteren Autor:innen. Die Arbeit nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
UML class diagram modeling is a fundamental task in software engineering, yet the application of large language models (LLMs) to this domain remains underexplored. Existing studies predominantly focus on single closed-source models with simple prompting strategies, lacking systematic comparisons across model types, prompt engineering techniques, and iterative refinement approaches. In this paper, we construct a difficulty-stratified dataset of 30 UML class diagram exercises and propose an automated weighted evaluation metric over generated PlantUML code—both of which are rarely constructed and systematically applied in existing LLM-driven UML modeling research. We present a preliminary empirical evaluation comparing open-source and closed-source LLMs across multiple scales and types, diverse prompting strategies, and varying requirement complexity levels. Beyond the single-round static paradigm of prior work, we further introduce and evaluate iterative prompting schemes that continuously improve model outputs through structured feedback. Our findings reveal that chain-of-thought prompting has different effects on improving the quality of different models, that relationship modeling is the persistent bottleneck under increasing complexity, and attribute extraction remains a largely unsolved technical challenge across all tested LLMs. Further, automated feedback-driven iterative refinement yields varied improvements: it brings notable performance gains for reasoning-oriented thinking models while delivering only marginal promotion for high-performance general chat models. These results provide actionable guidance for practitioners and researchers applying LLMs to UML modeling tasks.
Zitieren
APA
Cheng, Y., Huang, Y., Yao, S., Qian, Y., Zhang, L., Fang, X., & Wu, T. (2026). Large Language Models for UML Class Diagram Modeling: A Preliminary Empirical Evaluation. Applied Sciences, 16(13), 6540. https://doi.org/10.3390/app16136540
Vancouver
Cheng Y, Huang Y, Yao S, Qian Y, Zhang L, Fang X, et al. Large Language Models for UML Class Diagram Modeling: A Preliminary Empirical Evaluation. Applied Sciences. 2026;16(13):6540. doi:10.3390/app16136540
BibTeX
@article{Cheng2026,
author = {Cheng, Yong and Huang, You and Yao, Shixin and Qian, Yue and Zhang, Liang and Fang, Xueyin and Wu, Tianjun},
title = {Large Language Models for UML Class Diagram Modeling: A Preliminary Empirical Evaluation},
journal = {Applied Sciences},
year = {2026},
volume = {16},
number = {13},
pages = {6540},
doi = {10.3390/app16136540}
}
EUVIMED