Automated Feedback on Student-Generated UML and ER Diagrams Using Large Language Models
This addresses a problem for computer science educators and students by offering an incremental tool to improve feedback in large classes, though it is domain-specific to modeling education.
The paper tackled the challenge of providing scalable, personalized feedback on UML and ER diagrams in computer science education by developing DUET, an LLM-based tool that converts diagrams to text and generates structured feedback, evaluated through interviews with six participants who noted strengths like accessibility and scalability.
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.