用可解释AI区分人类与多种大模型生成文本，准确率超98%。
Leveraging Explainable AI for LLM Text Attribution: Differentiating Human-Written and Multiple LLMs-Generated Text
- 结合机器学习与可解释AI，识别不同大模型生成文本特征。
- 多分类准确率达98.5%，显著高于GPTZero的78.3%。
- 揭示文本风格与结构差异，助力防抄袭与内容溯源。
生成式人工智能大语言模型（LLMs）的兴起引发了对生成内容来源识别的担忧。学生过度依赖此类工具可能影响写作或编程能力发展，并引发抄袭问题。本研究旨在支持检测和识别由大模型生成的文本。我们假设大模型生成文本可通过机器学习（ML）识别，并探究能够区分多个大模型生成文本的模型。采用随机森林（RF）、循环神经网络（RNN）等算法，结合可解释人工智能（XAI）分析关键特征。方法分为两类：1）二分类区分人类与AI文本；2）多分类区分人类文本与五种大模型（ChatGPT、LLaMA、Google Bard、Claude、Perplexity）生成文本。结果表明，多分类与二分类均表现优异。模型准确率达98.5%，优于GPTZero的78.3%。值得注意的是，GPTZero无法识别约4.2%的样本，而本模型可完整识别测试集。XAI结果显示，跨类别特征重要性分析可构建详细的作者/来源画像，通过突出独特风格与结构特征，增强内容原创性验证能力。
原文摘要 · Abstract (English)
The development of Generative AI Large Language Models (LLMs) raised the alarm regarding identifying content produced through generative AI or humans. In one case, issues arise when students heavily rely on such tools in a manner that can affect the development of their writing or coding skills. Other issues of plagiarism also apply. This study aims to support efforts to detect and identify textual content generated using LLM tools. We hypothesize that LLMs-generated text is detectable by machine learning (ML), and investigate ML models that can recognize and differentiate texts generated by multiple LLMs tools. We leverage several ML and Deep Learning (DL) algorithms such as Random Forest (RF), and Recurrent Neural Networks (RNN), and utilized Explainable Artificial Intelligence (XAI) to understand the important features in attribution. Our method is divided into 1) binary classification to differentiate between human-written and AI-text, and 2) multi classification, to differentiate between human-written text and the text generated by the five different LLM tools (ChatGPT, LLaMA, Google Bard, Claude, and Perplexity). Results show high accuracy in the multi and binary classification. Our model outperformed GPTZero with 98.5\% accuracy to 78.3\%. Notably, GPTZero was unable to recognize about 4.2\% of the observations, but our model was able to recognize the complete test dataset. XAI results showed that understanding feature importance across different classes enables detailed author/source profiles. Further, aiding in attribution and supporting plagiarism detection by highlighting unique stylistic and structural elements ensuring robust content originality verification.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。