Comparative Analysis of Large Language Models for Automated Use Case Diagram Generation

Nikhil Krishnan G S, Ambadi S, M G Thushara

2025

Abstract

This study explores the use of Large Language Models in automating the process of generating use case diagrams from software requirements written in natural language, ensuring both syntactic correctness and semantic accuracy. The proposed methodology involves selecting a few prominent LLMs, preparing standard-ized inputs, and assessing outputs based on their syntactic and semantic correctness, and relationship mapping. Models were compared using a rigorous error analysis framework to identify strengths and limitations of the models. Among the tested models, gemma2 achieved the best average performance. This research contributes to advancing automated requirements processing, offering a scalable solution for software engineering workflows.

Paper Citation

in Harvard Style

G S N., S A. and Thushara M. (2025). Comparative Analysis of Large Language Models for Automated Use Case Diagram Generation. In Proceedings of the 3rd International Conference on Futuristic Technology - Volume 2: INCOFT; ISBN 978-989-758-763-4, SciTePress, pages 465-471. DOI: 10.5220/0013594700004664

in Bibtex Style

@conference{incoft25,
author={Nikhil Krishnan G S and Ambadi S and M G Thushara},
title={Comparative Analysis of Large Language Models for Automated Use Case Diagram Generation},
booktitle={Proceedings of the 3rd International Conference on Futuristic Technology - Volume 2: INCOFT},
year={2025},
pages={465-471},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013594700004664},
isbn={978-989-758-763-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 3rd International Conference on Futuristic Technology - Volume 2: INCOFT
TI - Comparative Analysis of Large Language Models for Automated Use Case Diagram Generation
SN - 978-989-758-763-4
AU - G S N.
AU - S A.
AU - Thushara M.
PY - 2025
SP - 465
EP - 471
DO - 10.5220/0013594700004664
PB - SciTePress