Exploring the ChatGPT Approach for Bidirectional Traceability Problem between Design Models and Code

TL;DR

This paper investigates how ChatGPT can be used to address the bidirectional traceability problem between design models and code, demonstrating its potential to generate and correct models from natural language requirements.

Contribution

It demonstrates the feasibility of using ChatGPT for bidirectional traceability between design models and code, highlighting its ability to generate and correct models from natural language inputs.

Findings

ChatGPT can generate design models and code from natural language requirements.

ChatGPT can provide corrections to ensure consistency between models and code.

Bidirectional traceability is feasible using ChatGPT despite some limitations.

Abstract

This study explores the capabilities of Large Language Models, particularly OpenAI's ChatGPT, in addressing the challenges associated with software modeling, explicitly focusing on the bidirectional traceability problem between design models and code. The objective of this study is to demonstrate the proficiency of ChatGPT in understanding and integrating specific requirements into design models and code. We also explore its potential to offer solutions to the bidirectional traceability problem through a case study. The findings indicate that ChatGPT is capable of generating design models and code from natural language requirements, thereby bridging the gap between these requirements and software modeling. Despite its limitations in suggesting a specific method to resolve the problem using ChatGPT itself, it exhibited the capacity to provide corrections to be consistent between design models and code. As a result, the study concludes that achieving bidirectional traceability between design models and code is feasible using ChatGPT.