arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.04449cs.AI
收藏

使用GPT-4为编程练习生成反馈

Feedback-Generation for Programming Exercises With GPT-4

LMU Munich(慕尼黑大学);Nuremberg Tech(纽伦堡应用技术大学)

Imen Azaiz, Natalie Kiesler, Sven Strickroth

AI总结:

本文评估了GPT-4 Turbo在入门编程课程中为学生提交生成反馈的质量,发现其相比GPT-3.5在结构化、一致性和错误定位等方面有显著改进,同时揭示了仍存在的不一致反馈问题。

摘要:

自从大型语言模型(LLMs)及相关应用广泛可用以来,已有若干研究探讨了它们在高等教育中辅助教育者和支持学生的潜力。Codex、GPT-3.5和GPT-4等LLMs在大型编程课程中已展现出有前景的结果,因为如果反馈和提示能够及时且大规模地提供,学生可以从中受益。本文探讨了GPT-4 Turbo针对同时包含编程任务说明和学生提交内容的提示所生成输出的质量。研究选取了一门入门编程课程中的两项作业,并要求GPT-4为55份随机选取的真实学生编程提交生成反馈。我们对输出进行了定性分析,考察正确性、个性化、错误定位以及材料中识别出的其他特征。与先前工作及对GPT-3.5的分析相比,GPT-4 Turbo表现出显著改进。例如,其输出更加结构化且一致。GPT-4 Turbo还能准确识别学生程序输出中的无效大小写。在某些情况下,反馈还包含学生程序的输出。与此同时,也注意到不一致的反馈,例如声称提交是正确的,但又指出有一个错误需要修复。本研究增进了我们对LLMs潜力、局限性以及如何将其整合到电子评估系统、教学场景以及指导使用基于GPT-4应用的学生方面的理解。

英文摘要:

Ever since Large Language Models (LLMs) and related applications have become broadly available, several studies investigated their potential for assisting educators and supporting students in higher education. LLMs such as Codex, GPT-3.5, and GPT 4 have shown promising results in the context of large programming courses, where students can benefit from feedback and hints if provided timely and at scale. This paper explores the quality of GPT-4 Turbo's generated output for prompts containing both the programming task specification and a student's submission as input. Two assignments from an introductory programming course were selected, and GPT-4 was asked to generate feedback for 55 randomly chosen, authentic student programming submissions. The output was qualitatively analyzed regarding correctness, personalization, fault localization, and other features identified in the material. Compared to prior work and analyses of GPT-3.5, GPT-4 Turbo shows notable improvements. For example, the output is more structured and consistent. GPT-4 Turbo can also accurately identify invalid casing in student programs' output. In some cases, the feedback also includes the output of the student program. At the same time, inconsistent feedback was noted such as stating that the submission is correct but an error needs to be fixed. The present work increases our understanding of LLMs' potential, limitations, and how to integrate them into e-assessment systems, pedagogical scenarios, and instructing students who are using applications based on GPT-4.

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。

↑