arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.07081cs.CLcs.SE
收藏

在计算机科学教育中使用大型语言模型进行学生代码引导的测试用例生成

Using Large Language Models for Student-Code Guided Test Case Generation in Computer Science Education

University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校)

Nischal Ashok Kumar, Andrew Lan

AI总结:

本文提出一种基于大型语言模型的自动化测试用例生成方法,利用包含学生Java代码的公开数据集验证其能有效衡量学生知识,为计算机科学教育提供个性化反馈并降低人工成本。

摘要:

在计算机科学教育中,测试用例是编程作业不可或缺的一部分,因为它们可以作为评估项目来测试学生的编程知识,并针对学生编写的代码提供个性化反馈。我们工作的目标是提出一种完全自动化的测试用例生成方法,以准确衡量学生的知识,这很重要,原因有两点。首先,手动构建测试用例需要专家知识,且是一个劳动密集型的过程。其次,为学生开发测试用例,尤其是为新手程序员,与面向专业级软件开发人员的测试用例有显著不同。因此,我们需要一个自动化的测试用例生成过程来评估学生知识并提供反馈。在这项工作中,我们提出了一种基于大型语言模型的方法来自动生成测试用例,并使用一个包含学生编写的Java代码的公开数据集,证明它们是衡量学生知识的良好标准。我们还讨论了以使用测试用例帮助学生为中心的未来研究方向。

英文摘要:

In computer science education, test cases are an integral part of programming assignments since they can be used as assessment items to test students' programming knowledge and provide personalized feedback on student-written code. The goal of our work is to propose a fully automated approach for test case generation that can accurately measure student knowledge, which is important for two reasons. First, manually constructing test cases requires expert knowledge and is a labor-intensive process. Second, developing test cases for students, especially those who are novice programmers, is significantly different from those oriented toward professional-level software developers. Therefore, we need an automated process for test case generation to assess student knowledge and provide feedback. In this work, we propose a large language model-based approach to automatically generate test cases and show that they are good measures of student knowledge, using a publicly available dataset that contains student-written Java code. We also discuss future research directions centered on using test cases to help students.

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。

↑