Optimal Estimation of Watermark Proportions in Hybrid AI-Human Texts

arXiv:2506.22343 · stat.ML, cs.CL, cs.LG, stat.ME · Submitted 2025-06-27 · Read on arXiv

stat.ML, cs.CL, cs.LG, stat.ME

Submitted: 2025-06-27

Updated: 2026-08-30

Code: https://github.com/lx10077/WatermarkProportion

Terminology

• Accuracy — 24× in this paper · explained in 1 episode
• Verifier — 14× in this paper · explained in 2 episodes
• Regularization — 4× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 3× in this paper · explained in 6 episodes
• Kullback-Leibler (KL) Divergence — 2× in this paper · explained in 3 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Theoretical Guarantees — 2× in this paper · explained in 2 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Verification — 2× in this paper · explained in 2 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Decoupling — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• Minimax optimality — 1× in this paper · explained in 2 episodes
• Objective Function — 1× in this paper · explained in 2 episodes
• Phase Transitions — 1× in this paper · explained in 2 episodes
• Transfer Learning — 1× in this paper · explained in 10 episodes

Sources

• On the Opportunities and Risks of Foundation Models
• Under the Surface: Tracking the Artifactuality of LLM-Generated Data
• The Llama 3 Herd of Models
• Mark My Words: Analyzing and Evaluating Language Model Watermarks
• A Resilient and Accessible Distribution-Preserving Watermark for Large Language Models
• Debiasing Watermarks for Large Language Models via Maximal Coupling
• Measuring Human Contribution in AI-Assisted Content Generation
• OPT: Open Pre-trained Transformer Language Models
• Permute-and-Flip: An optimally stable and watermarkable decoder for LLMs
• Efficiently Identifying Watermarked Segments in Mixed-Source Texts

Related papers

• Behavior of prediction performance metrics with rare events
• Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
• A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
• One Permutation Is All You Need: Fast, Deterministic Feature Importance and Model Stress-Testing
• Online Conformal Prediction for Non-Exchangeable Panel Data
• Deep Time-Series Forecasting in 10 Years: A Survey