ClockMark: Adaptive and Host-Dependent Watermarking for Large Language Models
arXiv:2610.27079v1 Announce Type: new Abstract: Large language model (LLM) watermarking operates on the next-token distribution that evolves during generation. In streaming generation, each sampled token becomes part of the text and affects subsequent distributions. Embedding therefore proceeds wit…
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-10-21 04:00 · arXiv cs.LG
ClockMark: Adaptive and Host-Dependent Watermarking for Large Language Models