用序列模型让AI写的文本更像人写，骗过检测器。
Transforming Chatbot Text: A Sequence-to-Sequence Approach
- 用T5-small和BART修改GPT文本，加入人类写作特征。
- 改造后文本使检测模型准确率大幅下降，从90%以上降至不足60%。
- 既可用于绕过检测，也可用于训练更强的识别模型。
随着大型语言模型（如ChatGPT）的发展，人工撰写与AI生成文本的界限变得模糊。尽管已有研究能可靠检测GPT生成文本，本文提出一种新策略：利用序列到序列（Seq2Seq）模型对抗性地转换GPT生成文本，使其更接近人类写作风格。实验采用T5-small和BART模型，对GPT生成句子进行修改，引入更符合人类语言习惯的语义、结构和语言特征。结果表明，训练用于区分GPT文本的分类模型在处理经此方法改造的文本时，准确率显著下降——从超过90%降至不足60%。然而，当使用这些改造后的数据重新训练分类模型后，其对改造后文本的识别准确率再次提升至高水平。本工作揭示了文本转换在攻击（规避检测）与防御（增强检测）中的双重作用，深化了对生成文本特性的理解。
原文摘要 · Abstract (English)
Due to advances in Large Language Models (LLMs) such as ChatGPT, the boundary between human-written text and AI-generated text has become blurred. Nevertheless, recent work has demonstrated that it is possible to reliably detect GPT-generated text. In this paper, we adopt a novel strategy to adversarially transform GPT-generated text using sequence-to-sequence (Seq2Seq) models, with the goal of making the text more human-like. We experiment with the Seq2Seq models T5-small and BART which serve to modify GPT-generated sentences to include linguistic, structural, and semantic components that may be more typical of human-authored text. Experiments show that classification models trained to distinguish GPT-generated text are significantly less accurate when tested on text that has been modified by these Seq2Seq models. However, after retraining classification models on data generated by our Seq2Seq technique, the models are able to distinguish the transformed GPT-generated text from human-generated text with high accuracy. This work adds to the accumulating knowledge of text transformation as a tool for both attack -- in the sense of defeating classification models -- and defense -- in the sense of improved classifiers -- thereby advancing our understanding of AI-generated text.
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。