STAF 2025
Tue 10 - Fri 13 June 2025 Koblenz, Germany
Wed 11 Jun 2025 13:50 - 14:10 at D 238 - AgileMDE Session 2: LLMs and Formal Methods

Large Language Models (LLMs) are increasingly applied to many different software tasks, and by means of specific domain training, they can perform well in specialised areas. Code-aware LLMs can generate executable program code from natural language specifications and prompts, but there are questions about the reliability of this process, because the results are not always consistent and correct. Model-driven engineering (MDE) also provides code generation techniques, which produce code automatically based on software designs expressed in UML or OCL. Compared to the LLM solution, the code generation process in MDE is more explicit, and the transformed code is determined by the source model, and there is usually a high correctness level for such generation. The code-generation by example (CGBE) process uses symbolic machine learning to synthesise code generators for particular code generation processes in MDE. The resulting generators map from UML/OCL specifications to the target programming language. In this paper we compare the effectiveness of code generation using baseline and fine-tuned LLMs, such as DeepSeek and LLama2, with CGBE code generators.

Wed 11 Jun

Displayed time zone: Amsterdam, Berlin, Bern, Rome, Stockholm, Vienna change


Information for Participants
Wed 11 Jun 2025 13:30 - 15:00 at D 238 - AgileMDE Session 2: LLMs and Formal Methods
Info for session

Session 2: “Leveraging LLMs and Formal Methods in Agile MDE”

Time: 13:30 – 15:00
Location: A 308

Description:
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