Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense Kalpesh Krishna Yixiao Song John Wieting

The rise in malicious usage of large language models, such as fake content creation and academic plagiarism, has motivated the development of approaches that identify AI-generated text, including those based on watermarking or outlier detection. However, the robustness of these detection algorithms to paraphrases of AI-generated text remains unclear.