A RAG-based Feedback Tool to Augment UML Class Diagram Learning
Pasquale Ardimento, Mario Luca Bernardi, Marta Cimitile, Michele Scalera · 2024
This paper introduces an advanced functionality designed to facilitate the learning of UML class diagram construction. Built upon an integrated Retrieval Augmented Generation Large Language Model, the functionality provides enriched feedback by leveraging accumulated knowledge. The functionality is implemented in an existing tool named UML Miner, a Visual Paradigm plugin that captures and analyzes student-generated UML diagrams by applying process mining techniques. By offering personalized feedback and continuous support during modeling, the tool aims to enhance learning outcomes and students' engagement.