arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2404.06371cs.SEcs.CLcs.LG
收藏

基于大语言模型的模型生成:从需求到UML序列图

Model Generation with LLMs: From Requirements to UML Sequence Diagrams

Consiglio Nazionale delle Ricerche (CNR)(国家研究委员会(CNR));SnT University of Luxembourg(卢森堡大学SnT学院);Monash University(莫纳什大学)

Alessio Ferrari, Sallam Abualhaija, Chetan Arora

AI总结:

本文研究了ChatGPT从自然语言需求生成UML序列图的能力,通过对28份需求文档的定性分析发现,生成模型虽符合标准且可理解,但在需求存在歧义和不一致时完整性与正确性不足,为RE领域应用LLM及提示策略设计提供了启示。

摘要:

用图形化模型补充自然语言(NL)需求可以改善利益相关者的沟通,并为系统设计提供方向。然而,从需求创建模型涉及人工工作。生成式大语言模型(LLMs)的出现,ChatGPT是一个显著例子,为模型生成中的自动化辅助提供了有前景的途径。本文研究了ChatGPT从自然语言需求生成特定类型模型,即UML序列图的能力。我们进行了一项定性研究,考察了ChatGPT为来自不同领域、不同类型的28份需求文档生成的序列图。通过对生成图的分析,观察结果被系统地记录在评估日志中,并通过主题分析进行分类。我们的结果表明,尽管这些模型通常符合标准并表现出合理的可理解性,但它们在指定需求方面的完整性和正确性往往存在挑战。当存在需求异味(如歧义和不一致)时,这一问题尤为突出。本研究得出的见解可以影响大语言模型在需求工程(RE)过程中的实际应用,并为针对有效模型生成的新型RE特定提示策略打开大门。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑