Text Watermarking Explained: Biasing Logits Based on History
a_karvonen · x · 2026-08-17
The author provides a concise technical explanation of text watermarking: during sampling, bias the logits based on the last N tokens. While this changes the sampling distribution at each position, the biases mostly cancel out in aggregate, mostly preserving the overall output distribution.
Related event: Multiple Technical Authors Break Down How LLM Text Watermarking Works(5 posts)→
More from Safety
- Linux Kernel CVEs Surge From ~500 to 1500+ Per Release, LLMs Blamed for Bulk of the Rise — burny_tech · 2026-10-03
- COLM 2026 Launches DAIH Workshop on Deploying LLMs/VLMs Responsibly in Healthcare — StellaLisy · 2026-10-03
- Trillium Labs wants to do open research on recursive self-improvement and agents — nordicinst · 2026-10-03
- Trillium Labs Wants to Research Self-Improvement and Model Behavior in the Open — Wired AI · 2026-10-03
- Cloudflare Turnstile everywhere: anti-AI scraping walls now hit human users — sethlazar · 2026-10-02
- Filler tokens let frontier models reason invisibly: 13-point gains undetectable by CoT monitoring — PandaAshwinee · 2026-10-02