论文标题
用验证的语言模型欺骗苔藓的检测
Fooling MOSS Detection with Pretrained Language Models
论文作者
论文摘要
随着人工智能（AI）技术在社会中变得越来越强大和突出，他们的滥用就是日益关注的问题。在教育环境中，学生可以使用AI技术来欺骗作业和考试。在本文中，我们探讨了是否可以使用变形金刚来求解介绍级的编程作业，同时绕过常用的AI工具来检测软件部分之间的相似性。我们发现使用GPT-J [Wang和Komatsuzaki，2021]的学生可以完成入门级的编程作业，而无需触发MOSS的怀疑[Aiken，2000]，这是一种广泛使用的软件相似性和窃遗传检测工具。尽管事实上GPT-J没有接受有关问题的培训，也没有提供任何示例可供工作。我们进一步发现，GPT-J编写的代码在结构上是多种多样的，缺乏任何特定的告诉未来的窃检测技术可能会用来尝试识别算法生成的代码。最后，我们讨论了大语言模型的道德和教育含义以及未来研究的方向。
As artificial intelligence (AI) technologies become increasingly powerful and prominent in society, their misuse is a growing concern. In educational settings, AI technologies could be used by students to cheat on assignments and exams. In this paper we explore whether transformers can be used to solve introductory level programming assignments while bypassing commonly used AI tools to detect similarities between pieces of software. We find that a student using GPT-J [Wang and Komatsuzaki, 2021] can complete introductory level programming assignments without triggering suspicion from MOSS [Aiken, 2000], a widely used software similarity and plagiarism detection tool. This holds despite the fact that GPT-J was not trained on the problems in question and is not provided with any examples to work from. We further find that the code written by GPT-J is diverse in structure, lacking any particular tells that future plagiarism detection techniques may use to try to identify algorithmically generated code. We conclude with a discussion of the ethical and educational implications of large language models and directions for future research.
