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 2602.22456cs.SEcs.AI
收藏

利用大语言模型自动化检测需求依赖

Automating the Detection of Requirement Dependencies Using Large Language Models

University of Ottawa(渥太华大学);École de technologie supérieure(超技术学院);Research Ireland Lero Centre for Software Research(爱尔兰Lero软件研究中心);University of Limerick(利默里克大学);General Motors(通用汽车公司)

Ikram Darif, Feifei Niu, Manel Abdellatif, Lionel C. Briand, Ramesh S., Arun Adiththan

AI总结:

本文提出LEREDD,一种基于大语言模型的自动化需求依赖检测方法,利用RAG和ICL技术,实现高准确率的依赖分类和细粒度依赖检测。

摘要:

需求通过各种类型的依赖相互关联。识别这些依赖关系至关重要,因为它们支撑着关键决策,并影响软件开发过程中的各种活动。然而,这一任务具有挑战性,尤其是在现代软件系统中,由于复杂且耦合的需求数量庞大。这些挑战进一步加剧了自然语言(NL)需求的模糊性和其持续变化。因此,需求依赖检测往往被忽视或手动完成。大语言模型(LLMs)在自然语言处理方面表现出强大的能力,为需求相关任务提供了一个有前途的途径。尽管它们已显示出增强各种需求工程任务的能力,但在识别需求依赖方面的效果尚未被探索。在本文中,我们介绍了LEREDD,一种基于LLM的自动化需求依赖检测方法,利用检索增强生成(RAG)和上下文学习(ICL)。它旨在直接从自然语言需求中识别多种依赖类型。我们通过与两个最先进的基线进行实证评估。结果表明,LEREDD能够提供高准确率的依赖和非依赖需求分类,准确率为0.93,F1得分为0.84,后者在非依赖情况下的平均值为0.96。LEREDD在检测细粒度依赖类型方面优于零样本LLM和基线,其中在Requires依赖上,其F1得分比基线分别高出94.87%和105.41%。我们还提供了一个包含三个不同系统中813对需求的注释依赖数据集,以支持可重复性和未来研究。

英文摘要:

Requirements are inherently interconnected through various types of dependencies. Identifying these dependencies is essential, as they underpin critical decisions and influence a range of activities throughout software development. However, this task is challenging, particularly in modern software systems, given the high volume of complex, coupled requirements. These challenges are further exacerbated by the ambiguity of Natural Language (NL) requirements and their constant change. Consequently, requirement dependency detection is often overlooked or performed manually. Large Language Models (LLMs) exhibit strong capabilities in NL processing, presenting a promising avenue for requirement-related tasks. While they have shown to enhance various requirements engineering tasks, their effectiveness in identifying requirement dependencies remains unexplored. In this paper, we introduce LEREDD, an LLM-based approach for automated detection of requirement dependencies that leverages Retrieval-Augmented Generation (RAG) and In-Context Learning (ICL). It is designed to identify diverse dependency types directly from NL requirements. We empirically evaluate LEREDD against two state-of-the-art baselines. The results show that LEREDD provides highly accurate classification of dependent and non-dependent requirements, achieving an accuracy of 0.93, and an F1 score of 0.84, with the latter averaging 0.96 for non-dependent cases. LEREDD outperforms zero-shot LLMs and baselines, particularly in detecting fine-grained dependency types, where it yields average relative gains of 94.87% and 105.41% in F1 scores for the Requires dependency over the baselines. We also provide an annotated dataset of requirement dependencies encompassing 813 requirement pairs across three distinct systems to support reproducibility and future research.

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。

↑