文本中是否涉及ChatGPT?测量Polish Ratio以检测ChatGPT生成的文本
Is ChatGPT Involved in Texts? Measure the Polish Ratio to Detect ChatGPT-Generated Text
AI总结:
针对现有检测器无法识别人机协作文本的问题,提出HPPT数据集与Polish Ratio方法,通过量化ChatGPT对文本的修改程度来检测ChatGPT润色文本,在多个数据集上展现出更强的鲁棒性。
摘要:
ChatGPT等大规模语言模型在文本生成方面的卓越能力给读者留下了深刻印象,并促使研究人员设计检测器以减轻包括虚假信息、网络钓鱼和学术不端在内的潜在风险。尽管如此,以往的大多数研究主要集中在创建能够区分纯ChatGPT生成文本与人类撰写文本的检测器。然而,这种方法无法有效辨别通过人机协作生成的文本,例如经ChatGPT润色的文本。为解决这一空白,我们引入了一个名为HPPT(ChatGPT-polished academic abstracts,ChatGPT润色的学术摘要)的新颖数据集,以促进构建更鲁棒的检测器。该数据集与现有语料库不同,它包含成对的人类撰写摘要和ChatGPT润色摘要,而非纯ChatGPT生成的文本。此外,我们提出了“Polish Ratio”方法,这是一种创新性度量,用于衡量ChatGPT相对于原始人类撰写文本所做的修改程度。它提供了一种机制来衡量结果文本中ChatGPT影响的程度。我们的实验结果表明,我们提出的模型在HPPT数据集和两个现有数据集(HC3和CDB)上具有更好的鲁棒性。此外,我们提出的“Polish Ratio”通过量化ChatGPT的参与程度,提供了更全面的解释。
英文摘要:
The remarkable capabilities of large-scale language models, such as ChatGPT, in text generation have impressed readers and spurred researchers to devise detectors to mitigate potential risks, including misinformation, phishing, and academic dishonesty. Despite this, most previous studies have been predominantly geared towards creating detectors that differentiate between purely ChatGPT-generated texts and human-authored texts. This approach, however, fails to work on discerning texts generated through human-machine collaboration, such as ChatGPT-polished texts. Addressing this gap, we introduce a novel dataset termed HPPT (ChatGPT-polished academic abstracts), facilitating the construction of more robust detectors. It diverges from extant corpora by comprising pairs of human-written and ChatGPT-polished abstracts instead of purely ChatGPT-generated texts. Additionally, we propose the "Polish Ratio" method, an innovative measure of the degree of modification made by ChatGPT compared to the original human-written text. It provides a mechanism to measure the degree of ChatGPT influence in the resulting text. Our experimental results show our proposed model has better robustness on the HPPT dataset and two existing datasets (HC3 and CDB). Furthermore, the "Polish Ratio" we proposed offers a more comprehensive explanation by quantifying the degree of ChatGPT involvement.
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。