TextSeal2: Distortion-Free LLM Watermarking with Copula Mixing and Memoryless Races

TextSeal2 is a distortion‑free watermarking method for large language models that maintains signal integrity during speculative decoding. It merges multiple keys into a single virtual key using a Gaussian copula, ensuring that the acceptance rate and output diversity remain unchanged while adding no measurable inference latency. Experiments on three LLMs show that TextSeal2 detects 8–22 percentage points more 100‑token answers than its predecessor TextSeal and outperforms textGrain under speculative decoding, all without post‑logits optimization.

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 AI.

• llms
• efficiency