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 2403.16347cs.SEcs.AIcs.LG
收藏

软件评论中的ChatGPT错误检测

ChatGPT Incorrectness Detection in Software Reviews

University of Calgary(卡尔加里大学);York University(约克大学)

Minaoar Hossain Tanzil, Junaed Younus Khan, Gias Uddin

AI总结:

本研究针对从业者对ChatGPT在软件工程任务中回答真实性的担忧,开发了基于迭代提示和文本变形关系的CID工具,能以0.74-0.75的F1分数自动检测ChatGPT在软件库选择任务中的错误回答。

摘要:

我们对135名软件工程(SE)从业者进行了调查,以了解他们如何将基于生成式AI的聊天机器人(如ChatGPT)用于SE任务。我们发现他们希望将ChatGPT用于软件库选择等SE任务,但经常担心ChatGPT回答的真实性。我们开发了一套技术及名为CID(ChatGPT Incorrectness Detector)的工具,以自动测试和检测ChatGPT回答中的错误。CID基于对ChatGPT的迭代提示,通过提出上下文相似但文本发散的问题(利用文本中变形关系的方法)。CID的基本原理是:对于给定问题,与其他回答(在问题的多种变体中)不同的回答很可能是错误回答。在库选择的基准研究中,我们表明CID能以0.74 - 0.75的F1分数检测出ChatGPT的错误回答。

英文摘要:

We conducted a survey of 135 software engineering (SE) practitioners to understand how they use Generative AI-based chatbots like ChatGPT for SE tasks. We find that they want to use ChatGPT for SE tasks like software library selection but often worry about the truthfulness of ChatGPT responses. We developed a suite of techniques and a tool called CID (ChatGPT Incorrectness Detector) to automatically test and detect the incorrectness in ChatGPT responses. CID is based on the iterative prompting to ChatGPT by asking it contextually similar but textually divergent questions (using an approach that utilizes metamorphic relationships in texts). The underlying principle in CID is that for a given question, a response that is different from other responses (across multiple incarnations of the question) is likely an incorrect response. In a benchmark study of library selection, we show that CID can detect incorrect responses from ChatGPT with an F1-score of 0.74 - 0.75.

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。

↑