Toward a New Era of Rapid Development: Assessing GPT-4-Vision's Capabilities in UML-Based Code Generation

The emergence of advanced neural networks has opened up new ways in automated code generation from conceptual models, promising to enhance software development processes. This paper presents a preliminary evaluation of GPT-4-Vision, a state-of-the-art deep learning model, and its capabilities in tra...

Full description

Saved in:
Bibliographic Details
Published in2024 IEEE/ACM International Workshop on Large Language Models for Code (LLM4Code) pp. 84 - 87
Main Authors Antal, Gabor, Vozar, Richard, Ferenc, Rudolf
Format Conference Proceeding
LanguageEnglish
Published ACM 20.04.2024
Subjects
AI in Software Engineering
Code Generation
Codes
Java
Large language models
Neural networks
OOP
Software
Software development management
Software engineering
Software prototyping
Source coding
UML
Unified modeling language
Online AccessGet full text
DOI10.1145/3643795.3648391

Cover

More Information
Summary:The emergence of advanced neural networks has opened up new ways in automated code generation from conceptual models, promising to enhance software development processes. This paper presents a preliminary evaluation of GPT-4-Vision, a state-of-the-art deep learning model, and its capabilities in transforming Unified Modeling Language (UML) class diagrams into fully operating Java class files. In our study, we used exported images of 18 class diagrams comprising 10 single-class and 8 multi-class diagrams. We used 3 different prompts for each input, and we manually evaluated the results. We created a scoring system in which we scored the occurrence of elements found in the diagram within the source code. On average, the model was able to generate source code for 88% of the elements shown in the diagrams. Our results indicate that GPT-4-Vision exhibits proficiency in handling single-class UML diagrams, successfully transforming them into syntactically correct class files. However, for multi-class UML diagrams, the model's performance is weaker compared to single-class diagrams. In summary, further investigations are necessary to exploit the model's potential completely.CCS CONCEPTS* Software and its engineering → Software prototyping.
DOI:10.1145/3643795.3648391