Model Generation with LLMs: From Requirements to UML Sequence Diagrams

TL;DR

This study explores ChatGPT's ability to generate UML sequence diagrams from natural language requirements, highlighting its strengths in conforming to standards and understandability, but also noting challenges in completeness and correctness, especially with ambiguous or inconsistent inputs.

Contribution

The paper provides a qualitative analysis of ChatGPT's effectiveness in generating UML sequence diagrams from diverse natural language requirements, revealing strengths and limitations.

Findings

Models generally conform to UML standards

Generated diagrams are reasonably understandable

Completeness and correctness are often challenged by ambiguous requirements

Abstract

Complementing natural language (NL) requirements with graphical models can improve stakeholders' communication and provide directions for system design. However, creating models from requirements involves manual effort. The advent of generative large language models (LLMs), ChatGPT being a notable example, offers promising avenues for automated assistance in model generation. This paper investigates the capability of ChatGPT to generate a specific type of model, i.e., UML sequence diagrams, from NL requirements. We conduct a qualitative study in which we examine the sequence diagrams generated by ChatGPT for 28 requirements documents of various types and from different domains. Observations from the analysis of the generated diagrams have systematically been captured through evaluation logs, and categorized through thematic analysis. Our results indicate that, although the models generally conform to the standard and exhibit a reasonable level of understandability, their completeness and correctness with respect to the specified requirements often present challenges. This issue is particularly pronounced in the presence of requirements smells, such as ambiguity and inconsistency. The insights derived from this study can influence the practical utilization of LLMs in the RE process, and open the door to novel RE-specific prompting strategies targeting effective model generation.