Evaluating Large Language Models in Exercises of UML Class Diagram Modeling
Daniele De Bari, Giacomo Garaccione, Riccardo Coppola, Marco Torchiano, Luca Ardito
Abstract
Large Language Models (LLM) have rapidly affirmed in the latest years as a means to support or substitute human actors in a variety of tasks. LLM agents can generate valid software models, because of their inherent ability in evaluating textual requirements provided to them in the form of prompts.
Topics & Concepts
Class diagramCommunication diagramComputer scienceUnified Modeling LanguageSystems Modeling LanguageProgramming languageActivity diagramApplications of UMLUML toolClass (philosophy)Story-driven modelingState diagramObject Constraint LanguageSoftware engineeringArtificial intelligenceFinite-state machineSoftwareModel-Driven Software Engineering TechniquesSoftware Engineering ResearchSoftware System Performance and Reliability