On the Indistinguishability of Human v/s AI Generated Text

The paper examines how repeated paraphrasing, guided by human writing samples, can shift machine‑generated text toward the human distribution. In a multi‑sample setting where both human and AI responses are available for the same prompts, the authors demonstrate that iterative paraphrasing converges to the empirical human distribution under simple mixing and stability conditions. They provide an explicit convergence rate, extend the analysis to finite samples, and quantify how many human samples and paraphrasing rounds are needed to achieve a desired error level.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

• llms