Problem
Research questions and friction points this paper is trying to address.
LLMs
AI-generated text
human writing
paraphrasing tools
On the Indistinguishability of Human v/s AI Generated Text
🤖 AI Summary
研究利用人类写作样本策略性改写机器生成文本，使其更接近人类文本分布，以解决难以区分AI与人类生成文本的问题。
📝 Abstract
The rapid improvement of LLMs has made distinguishing AI-generated text from human writing a pressing problem. This challenge is further amplified by paraphrasing tools designed to make machine-generated text appear more "human". We study how access to human writing samples can be used to strategically paraphrase machine-generated responses toward the human distribution. Under a multi-sample setting with human and machine responses to the same prompts, we show that repeated paraphrasing moves the machine distribution toward the empirical human distribution under simple mixing and stability conditions. Our results derive an explicit convergence rate, extend the analysis to a finite-sample setting, and characterize how the required number of human samples and paraphrasing rounds scale with the desired error.
Innovation
Methods, ideas, or system contributions that make the work stand out.
paraphrasing
human distribution
convergence rate
🔎 Similar Papers
2024-06-21Journal of Artificial Intelligence ResearchCitations: 6
