| Title |
Towards automated evaluation of UML models in teaching software engineering |
| Authors |
Stulpinaitė, Guoda ; Jurgelaitis, Mantas |
| Full Text |
|
| Is Part of |
CEUR workshop proceedings: IVUS 2026: proceedings of the 31st international conference on information society and university studies (IVUS 2026), Kaunas, Lithuania, May 12, 2026 / edited by Audrius Lopata,Tomas Krilavičius, Ilona Veitaitė.. Aachen : CEUR-WS. 2026, vol. 4317, p. 1-9.. ISSN 1613-0073 |
| Keywords [eng] |
UML ; LLM ; model evaluation ; horizontal consistency ; vertical consistency |
| Abstract [eng] |
The teaching of Unified Modeling Language (UML) modeling in higher education requires continuous feedback and detailed evaluation of student’s models. However, manual evaluation of UML models is timeconsuming and requires significant effort from lecturers, particularly when evaluating syntactic correctness, semantic consistency, and vertical and horizontal consistency between models. This paper explores the possibility of an automated approach for providing feedback and preliminary evaluation of UML models in the educational process using rule-based validation and Large Language Models (LLMs). The proposed approach integrates UML metamodel validation, consistency checking, and LLM-based semantic analysis. |
| Published |
Aachen : CEUR-WS |
| Type |
Conference paper |
| Language |
English |
| Publication date |
2026 |
| CC license |
|
