Automated Feedback on Student-Generated UML and ER Diagrams Using Large Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911085586546688 |
|---|---|
| author | Gürtl, Sebastian Schimetta, Gloria Kerschbaumer, David Liut, Michael Steinmaurer, Alexander |
| author_facet | Gürtl, Sebastian Schimetta, Gloria Kerschbaumer, David Liut, Michael Steinmaurer, Alexander |
| contents | UML and ER diagrams are foundational in computer science education but come with challenges for learners due to the need for abstract thinking, contextual understanding, and mastery of both syntax and semantics. These complexities are difficult to address through traditional teaching methods, which often struggle to provide scalable, personalized feedback, especially in large classes. We introduce DUET (Diagrammatic UML & ER Tutor), a prototype of an LLM-based tool, which converts a reference diagram and a student-submitted diagram into a textual representation and provides structured feedback based on the differences. It uses a multi-stage LLM pipeline to compare diagrams and generate reflective feedback. Furthermore, the tool enables analytical insights for educators, aiming to foster self-directed learning and inform instructional strategies. We evaluated DUET through semi-structured interviews with six participants, including two educators and four teaching assistants. They identified strengths such as accessibility, scalability, and learning support alongside limitations, including reliability and potential misuse. Participants also suggested potential improvements, such as bulk upload functionality and interactive clarification features. DUET presents a promising direction for integrating LLMs into modeling education and offers a foundation for future classroom integration and empirical evaluation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_23470 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Automated Feedback on Student-Generated UML and ER Diagrams Using Large Language Models Gürtl, Sebastian Schimetta, Gloria Kerschbaumer, David Liut, Michael Steinmaurer, Alexander Human-Computer Interaction Artificial Intelligence UML and ER diagrams are foundational in computer science education but come with challenges for learners due to the need for abstract thinking, contextual understanding, and mastery of both syntax and semantics. These complexities are difficult to address through traditional teaching methods, which often struggle to provide scalable, personalized feedback, especially in large classes. We introduce DUET (Diagrammatic UML & ER Tutor), a prototype of an LLM-based tool, which converts a reference diagram and a student-submitted diagram into a textual representation and provides structured feedback based on the differences. It uses a multi-stage LLM pipeline to compare diagrams and generate reflective feedback. Furthermore, the tool enables analytical insights for educators, aiming to foster self-directed learning and inform instructional strategies. We evaluated DUET through semi-structured interviews with six participants, including two educators and four teaching assistants. They identified strengths such as accessibility, scalability, and learning support alongside limitations, including reliability and potential misuse. Participants also suggested potential improvements, such as bulk upload functionality and interactive clarification features. DUET presents a promising direction for integrating LLMs into modeling education and offers a foundation for future classroom integration and empirical evaluation. |
| title | Automated Feedback on Student-Generated UML and ER Diagrams Using Large Language Models |
| topic | Human-Computer Interaction Artificial Intelligence |
| url | https://arxiv.org/abs/2507.23470 |