SOURCE-LINKED INTELLIGENCE

Predictive Likelihood Ratios for Language Model Watermark Detection

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

Keyed watermark detection tests dependence between observed tokens and pseudorandom variables reconstructed from a secret key. Building on the pivotal framework of Li et al. (2025), we construct predictive likelihood ratios that average over uncertain probability deficits and residual-tail distributions. The aim is robust detection power across alternative specifications without requiring a single signal-strength tuning. A mixture prior combines tail shape and effective width; hierarchical extensions allow within-document variation in deficit or width. The test maximizes prior-averaged power a

Read original source ↗ Open in workspace

recordType

paper

region

Global