Optimal Estimation of Watermark Proportions in Hybrid AI-Human Texts
stat.ML, cs.CL, cs.LG, stat.ME
Submitted: 2025-06-27
Updated: 2026-08-30
Code: https://github.com/lx10077/WatermarkProportion
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
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
- Efficient quadratic entropy with distance sketches
- Embedding-Bias in Conditional Independence Testing
- From Log-Odds to Shapley Values: An Explanatory Geometry for the Weighted Naive Bayes Classifier