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 2404.06201cs.SEcs.AI
收藏

基于AI的开源软件工程工具:协同软件学习的机遇与挑战

Open-Source AI-based SE Tools: Opportunities and Challenges of Collaborative Software Learning

Beihang University(北京航空航天大学);Nanyang Technological University(南洋理工大学);Westlake University(西湖大学);University of Luxembourg(卢森堡大学)

Zhihao Lin, Wei Ma, Tao Lin, Yaowen Zheng, Jingquan Ge, Jun Wang, Jacques Klein, Tegawende Bissyande, Yang Liu, Li Li

AI总结:

本文针对开源AI软件工程工具面临的高质量敏感数据难共享问题,提出以联邦学习为核心的治理框架与协作指南,并分析代码数据异质性对联邦学习性能的影响。

摘要:

大语言模型(LLMs)已成为推动软件工程(SE)任务发展的重要工具,并在代码理解及其他方面展现出显著成效。与传统软件工程工具一样,开源协作是实现优秀产品的关键。然而,对于AI模型而言,核心需求在于数据。这些基于AI的软件工程模型之间的协作,取决于能否最大限度获取高质量数据来源。但是,数据(尤其是高质量数据)往往具有商业价值或敏感性,导致基于AI的开源软件工程项目较难获取这些数据。这一现实给软件工程社区中基于AI的软件工程工具的开发和改进带来了重大障碍。因此,研究人员需要寻找解决方案,使基于AI的开源软件工程模型能够利用不同组织的资源。为应对这一挑战,本立场论文探讨了一种促进开源AI模型访问多样化组织资源的解决方案,同时确保隐私和商业敏感性得到尊重。我们提出了一个以联邦学习(FL)为核心的治理框架,旨在在保护数据隐私和安全的同时,促进开源AI代码模型的联合开发与维护。此外,我们还为开发者提供了关于基于AI的软件工程工具协作的指南,涵盖数据需求、模型架构、更新策略和版本控制。鉴于数据特征对FL具有显著影响,本研究考察了代码数据异质性对FL性能的影响。

英文摘要:

Large Language Models (LLMs) have become instrumental in advancing software engineering (SE) tasks, showcasing their efficacy in code understanding and beyond. Like traditional SE tools, open-source collaboration is key in realising the excellent products. However, with AI models, the essential need is in data. The collaboration of these AI-based SE models hinges on maximising the sources of high-quality data. However, data especially of high quality, often holds commercial or sensitive value, making it less accessible for open-source AI-based SE projects. This reality presents a significant barrier to the development and enhancement of AI-based SE tools within the software engineering community. Therefore, researchers need to find solutions for enabling open-source AI-based SE models to tap into resources by different organisations. Addressing this challenge, our position paper investigates one solution to facilitate access to diverse organizational resources for open-source AI models, ensuring privacy and commercial sensitivities are respected. We introduce a governance framework centered on federated learning (FL), designed to foster the joint development and maintenance of open-source AI code models while safeguarding data privacy and security. Additionally, we present guidelines for developers on AI-based SE tool collaboration, covering data requirements, model architecture, updating strategies, and version control. Given the significant influence of data characteristics on FL, our research examines the effect of code data heterogeneity on FL performance.

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。

↑