Model Generation with LLMs: From Requirements to UML Sequence Diagrams
This addresses the problem of manual effort in model generation for software engineering stakeholders, but it is incremental as it evaluates an existing LLM on a specific task without proposing new methods.
The paper investigated ChatGPT's ability to automatically generate UML sequence diagrams from natural language requirements, finding that while the diagrams generally conformed to standards and were understandable, they often lacked completeness and correctness, especially with ambiguous or inconsistent requirements.
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.