ClockMark makes LLM watermarks harder to edit without changing generation
ClockMark gives LLM developers a watermark that is more resistant to text editing while theoretically preserving the model’s original sequence distribution. It tracks earlier sampling decisions and uses the current next-token distribution to guide each new choice, then spreads the full message across every watermarked token. Across tests against 12 baselines, it improved bit accuracy by up to 16.08 percentage points over the strongest baseline.