一图胜千言：探索基于图表和视频的OOP练习以对抗对LLM的过度依赖
A Picture Is Worth a Thousand Words: Exploring Diagram and Video-Based OOP Exercises to Counter LLM Over-Reliance
AI总结：
针对学生过度依赖LLM完成OOP作业的学术诚信问题，研究提出基于图表和视频的OOP任务设计方法与新型符号系统，经一学期课堂实践与56名学生调研，该方法获积极反馈且能降低LLM依赖，同时GPT-4和Bard暂无法准确解读相关图表生成代码。
摘要：
大量研究已凸显出GPT、Bard等大语言模型（LLM）在解决入门级编程练习方面的出色能力。近期研究表明，LLM能够有效解决一系列带有文本规范的更复杂面向对象编程（OOP）练习。这引发了人们对学术诚信的担忧，因为学生可能会不道德地使用这些模型完成作业，忽视程序设计、问题解决和计算思维等重要技能的培养。为解决这一问题，我们提出了一种使用图表和视频设计OOP任务的创新方法，以此在OOP课程中培养问题解决能力，阻止学生采用“复制-提问”的应付方式。我们引入了一套用于明确OOP作业要求的新型符号系统，涵盖结构与行为需求，并在一整个学期的课堂环境中评估了其应用效果。我们通过一项样本量为56的调查探究了学生对该方法的看法。总体而言，学生对图表和视频的反馈积极，其中基于视频的项目比基于图表的练习更受好评。这套符号系统似乎具备多项优势：学生投入了更多精力理解图表，且参与基于视频的项目时积极性更高。此外，学生表示在完成这些基于图表和视频的练习时，不太倾向于依赖基于LLM的代码生成工具。针对GPT-4和Bard视觉能力的实验显示，它们目前在解读这些图表以生成准确代码解决方案方面仍有不足。
英文摘要：
Much research has highlighted the impressive capabilities of large language models (LLMs), like GPT and Bard, for solving introductory programming exercises. Recent work has shown that LLMs can effectively solve a range of more complex object-oriented programming (OOP) exercises with text-based specifications. This raises concerns about academic integrity, as students might use these models to complete assignments unethically, neglecting the development of important skills such as program design, problem-solving, and computational thinking. To address this, we propose an innovative approach to formulating OOP tasks using diagrams and videos, as a way to foster problem-solving and deter students from a copy-and-prompt approach in OOP courses. We introduce a novel notation system for specifying OOP assignments, encompassing structural and behavioral requirements, and assess its use in a classroom setting over a semester. Student perceptions of this approach are explored through a survey (n=56). Generally, students responded positively to diagrams and videos, with video-based projects being better received than diagram-based exercises. This notation appears to have several benefits, with students investing more effort in understanding the diagrams and feeling more motivated to engage with the video-based projects. Furthermore, students reported being less inclined to rely on LLM-based code generation tools for these diagram and video-based exercises. Experiments with GPT-4 and Bard's vision abilities revealed that they currently fall short in interpreting these diagrams to generate accurate code solutions.
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。
