Prevalence Bounds for Edited Watermarked Text: Power Envelopes and Calibration Sensitivity
stat.ML, cs.CL, cs.CR, cs.LG
Submitted: 2026-11-12
Updated: 2026-11-12
Code: https://github.com/YYKKCC-kevin/watermark-prevalence
Terminology
Sources
- Optimal Watermark Localization in Mixed-Source Large Language Model Texts
- Sample Complexities of Estimating Gumbel--Max Watermark Proportions with and without Reduction to Pivotal Statistics
- Reconciling Privacy with Provenance for Language Model Watermarks
- Towards Anytime-Valid Statistical Watermarking
- Optimal Estimation of Watermark Proportions in Hybrid AI-Human Texts
- Efficient Online LLM Watermark Detection via Rao-Blackwellized E-Processes
- Detecting Benchmark Contamination Through Watermarking
- Online LLM watermark detection via e-processes
- Qwen2.5 Technical Report
- Qwen3 Technical Report
- OPT: Open Pre-trained Transformer Language Models
Related papers
- Uniform-in-Time Weak Propagation-of-Chaos in Shallow Neural Networks
- Diffusion Models Observe Only Gradients: A Geometric Perspective on Score Matching Errors
- Quantifying Error Propagation and Model Collapse in Diffusion Models
- Behavior of prediction performance metrics with rare events
- Statistical Inference and Learning for Shapley Additive Explanations (SHAP)
- Control Variate Design for Score-Function Gradient Estimators in Importance-Weighted Variational Inference