Using LLMs to Extract UML Class Diagrams from Java and Python Programs: An Empirical Study
This program is tentative and subject to change.
In this paper, we present a comprehensive study of the capabilities of five large language models (LLMs), namely StarCoder2, LLaMA, CodeLlama, Mistral, and DeepSeek, for extracting UML class diagrams from code, with the aim to provide researchers and developers with insights into the capabilities and limitations of using various LLMs in a model-driven reverse engineering process. We evaluate the LLMs by prompting them to generate UML class diagrams for both Java and Python programs, with the key focus on accuracy, consistency, and F1-score.
This program is tentative and subject to change.
Wed 11 JunDisplayed time zone: Amsterdam, Berlin, Bern, Rome, Stockholm, Vienna change
13:30 - 15:00 | |||
13:30 20mPaper | Enhancing Agile Model-Driven Engineering with Automated Formal Verification of BPMN Models Agile MDE | ||
13:50 20mPaper | Comparing LLM-based and MDE-based Code Generation for Agile MDE Agile MDE | ||
14:10 20mPaper | Using LLMs to Extract UML Class Diagrams from Java and Python Programs: An Empirical Study Agile MDE | ||
14:30 20mPaper | Specification and design refactorings for sustainable agile model-driven engineering Agile MDE Dr Kevin Lano King's College London | ||
Session 2: “Leveraging LLMs and Formal Methods in Agile MDE”
Time: 13:30 – 15:00
Location: A 308Description:
This session dives into the integration of formal methods and large language models to advance Agile Model-Driven Engineering practices. Topics include automated verification of BPMN models, empirical studies on UML class diagram extraction using LLMs, and comparative evaluations of LLMs versus traditional MDE approaches for code generation. The session concludes with a focus on sustainable engineering through improved design refactorings.Papers:
- Enhancing Agile Model-Driven Engineering with Automated Formal Verification of BPMN Models - Kimia Kolahdouz, Shekoufeh Rahimi (University of Roehampton)
- Comparing LLM-based and MDE-based Code Generation for Agile MDE - Qiaomu Xue, Kevin Lano (King’s College London)
- Using LLMs to Extract UML Class Diagrams from Java and Python Programs: An Empirical Study - Hanan Abdulwahab Siala, Kevin Lano (King’s College London)
- Specification and design refactorings for sustainable agile model-driven engineering