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 2401.03676cs.SEcs.AI
收藏

评估AI检测器在识别AI生成代码中的表现:对教育的影响

Assessing AI Detectors in Identifying AI-Generated Code: Implications for Education

Monash University Malaysia(莫纳什大学马来西亚校区);Singapore Management University(新加坡管理大学)

Wei Hung Pan, Ming Jie Chok, Jonathan Leong Shan Wong, Yung Xin Shin, Yeong Shian Poon, Zhou Yang, Chun Yong Chong, David Lo, Mei Kuan Lim

AI总结:

本文评估了五种AIGC检测器在区分人工编写与ChatGPT生成的Python代码方面的能力,发现现有检测器表现不佳,揭示了教育领域面临的学术不端风险。

摘要:

教育工作者越来越关注在编程教育中使用诸如ChatGPT等大型语言模型(LLMs),特别是担忧可能利用人工智能生成内容(AIGC)检测器的不完善之处进行学术不端行为。本文提出了一项实证研究,考察LLM试图绕过AIGC检测器检测的行为。这是通过使用不同变体生成针对给定问题的代码来实现的。我们收集了一个包含5,069个样本的数据集,每个样本由编码问题的文本描述及其对应的人工编写的Python解决方案代码组成。这些样本来自多个来源,包括80个来自Quescol,3,264个来自Kaggle,1,725个来自LeetCode。从该数据集中,我们创建了13套代码问题变体提示,用于指导ChatGPT生成输出。随后,我们评估了五种AIGC检测器的性能。结果表明,现有的AIGC检测器在区分人工编写代码和AI生成代码方面表现不佳。

英文摘要:

Educators are increasingly concerned about the usage of Large Language Models (LLMs) such as ChatGPT in programming education, particularly regarding the potential exploitation of imperfections in Artificial Intelligence Generated Content (AIGC) Detectors for academic misconduct. In this paper, we present an empirical study where the LLM is examined for its attempts to bypass detection by AIGC Detectors. This is achieved by generating code in response to a given question using different variants. We collected a dataset comprising 5,069 samples, with each sample consisting of a textual description of a coding problem and its corresponding human-written Python solution codes. These samples were obtained from various sources, including 80 from Quescol, 3,264 from Kaggle, and 1,725 from LeetCode. From the dataset, we created 13 sets of code problem variant prompts, which were used to instruct ChatGPT to generate the outputs. Subsequently, we assessed the performance of five AIGC detectors. Our results demonstrate that existing AIGC Detectors perform poorly in distinguishing between human-written code and AI-generated code.

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。

↑