LLM-Driven Feedback for Enhancing Conceptual Design Learning in Database Systems Courses
Sara Riazi, Pedram Rooshenas
TL;DR
The paper tackles the challenge of providing high-quality, scalable feedback for conceptual database design by introducing an LLM-driven system that translates ERDs into JSON, prunes diagrams around specific relationships, and generates detailed, rubric-guided feedback plus FAQs. A per-relationship feedback paradigm, supported by educator-defined rubrics and questions, aims to overcome the limitations of diagram-wide feedback and constraint-based tutoring models. Empirical evidence from a DB course pilot shows substantial student-perceived value and learning gains, while expert evaluations highlight strong precision and areas for improved recall in complex constructs. Overall, the approach demonstrates a practical, scalable pathway to augment design education with intelligent, context-aware feedback that aligns with instructor goals and learning outcomes.
Abstract
The integration of LLM-generated feedback into educational settings has shown promise in enhancing student learning outcomes. This paper presents a novel LLM-driven system that provides targeted feedback for conceptual designs in a Database Systems course. The system converts student-created entity-relationship diagrams (ERDs) into JSON format, allows the student to prune the diagram by isolating a relationship, extracts relevant requirements for the selected relationship, and utilizes a large language model (LLM) to generate detailed feedback. Additionally, the system creates a tailored set of questions and answers to further aid student understanding. Our pilot implementation in a Database System course demonstrates effective feedback generation that helped the students improve their design skills.