Authors :
Martina Basic; Marko Vujasinovic
Volume/Issue :
Volume 11 - 2026, Issue 2 - February
Google Scholar :
https://tinyurl.com/3nupwn5f
Scribd :
https://tinyurl.com/28t9e2sf
DOI :
https://doi.org/10.38124/ijisrt/26feb1435
Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.
Abstract :
Large Language Models (LLMs) are becoming an increasingly important tool in the field of software engineering,
particularly in the automation of UML model creation based on requirements described in natural language. This paper
examines the effectiveness of applying LLM technologies to generate UML 2.5 state diagrams in PlantUML format from
textual system descriptions. The creation of state diagrams traditionally requires a strong understanding of the problem
domain and experience in formal modeling, and it is often a time-consuming and error-prone process. The automated
generation of UML state diagrams requires models to correctly identify system states, transitions between states, events,
guard conditions, as well as entry, exit, and internal activities, while adhering to the syntax and rules of UML 2.5 notation.
In the evaluation part of the study, three systems of varying levels of complexity were analyzed in order to assess the models’
ability to produce syntactically correct and semantically complete diagrams. Additionally, the impact of different prompt
design strategies on the quality of the generated results was examined. The results indicate that LLMs can effectively
generate state diagrams for simpler systems and significantly reduce the effort required for initial modeling. However, for
more complex systems, issues were observed in the consistent interpretation of requirements, the modeling of hierarchical
structures, and the preservation of system semantics. Overall, LLM technologies represent valuable support in the early
stages of UML state diagram development; however, the final quality of the models still largely depends on expert validation
and additional guidance provided by domain specialists.
Keywords :
LLM; UML State Machine Diagram; Prompt Engineering; Requirement Specification.
References :
- Nguyen, V.-V., Nguyen, H.-K., Nguyen, K.-S., Loung, T.M.-H., Vu, D.-Q., Phung, T.-N., and Nguyen, T.-V, 2026. A Novel Unified Framework for Automated Generation and Multimodal Validation of UML Diagrams. Computer Modeling in Engineering and Science, 146(1), https://doi.org/10.32604/cmes.2025.075442
- Cámara, J., Troya, J., Burgueño, L. and Vallecillo, A., 2023. On the assessment of generative AI in modeling tasks: an experience report with ChatGPT and UML. Software and Systems Modeling, 22(3), pp.781-793.
- Al-Ahmad, B., Alsobeh, A., Meqdadi, O. and Shaikh, N., 2025. A Student-Centric Evaluation Survey to Explore the Impact of LLMs on UML Modeling. Information, 16(7), p.565.
- Object Management Group, 2017. Unified Modeling Language (UML), version 2.5.1. https://www.omg.org/spec/UML/2.5.1/About-UML
- Basic, M., & Vujasinovic, M., 2026. Usage of LLM for Generation of UML Class Diagrams from UML Use-Case Diagrams. International Journal of Innovative Science and Research Technology, 11(1), https://doi.org/10.38124/ijisrt/26jan1576
- Jahan, M., Hasan, MM., Golpayegani, R., Roy, C. and Roy, B., 2024. Automated derivatio of UML sequence diagrams from user stories: unleashing the power of generative AI vs. rule-based approach. In Proceedings of the ACM/IEEE 27th International Coference on Model Driven Engineering Languages and Systems (MODELS ’24), p.p.138-48. https://doi.org/10.1145/3640310.3674081
Large Language Models (LLMs) are becoming an increasingly important tool in the field of software engineering,
particularly in the automation of UML model creation based on requirements described in natural language. This paper
examines the effectiveness of applying LLM technologies to generate UML 2.5 state diagrams in PlantUML format from
textual system descriptions. The creation of state diagrams traditionally requires a strong understanding of the problem
domain and experience in formal modeling, and it is often a time-consuming and error-prone process. The automated
generation of UML state diagrams requires models to correctly identify system states, transitions between states, events,
guard conditions, as well as entry, exit, and internal activities, while adhering to the syntax and rules of UML 2.5 notation.
In the evaluation part of the study, three systems of varying levels of complexity were analyzed in order to assess the models’
ability to produce syntactically correct and semantically complete diagrams. Additionally, the impact of different prompt
design strategies on the quality of the generated results was examined. The results indicate that LLMs can effectively
generate state diagrams for simpler systems and significantly reduce the effort required for initial modeling. However, for
more complex systems, issues were observed in the consistent interpretation of requirements, the modeling of hierarchical
structures, and the preservation of system semantics. Overall, LLM technologies represent valuable support in the early
stages of UML state diagram development; however, the final quality of the models still largely depends on expert validation
and additional guidance provided by domain specialists.
Keywords :
LLM; UML State Machine Diagram; Prompt Engineering; Requirement Specification.
