arXiv AI
Predictive Likelihood Ratios for Language Model Watermark Detection
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Jul 2
Sample Complexities of Estimating Gumbel--Max Watermark Proportions with and without Reduction to Pivotal Statistics
arXiv:2607. 00224v1 Announce Type: cross Abstract: Watermarking promises a statistical trace of large language model (LLM) use, but real documents, after editing or paraphrasing, rarely arrive as purely human-written or purely machine-generated.
arXiv Machine Learning
Jun 18
Signature filtering: a lightweight enhancement for statistical watermark detection in large language models
arXiv:2606. 18430v1 Announce Type: new Abstract: Statistical watermarks help organizations attribute large language model (LLM) outputs, yet existing detectors often struggle when watermark signals are weak, texts are repetitive, or watermarks are edited.
arXiv Machine Learning
Aug 18
Optimal Watermark Localization in Mixed-Source Large Language Model Texts
arXiv:2608. 14906v1 Announce Type: cross Abstract: Watermarking provides a principled way to authenticate text generated by large language models (LLMs).
arXiv Machine Learning
Sep 1
Optimal Estimation of Watermark Proportions in Hybrid AI-Human Texts
arXiv:2506.22343v2 Announce Type: replace-cross Abstract: Text watermarks in large language models (LLMs) are an increasingly important tool for detecting synthetic text and distinguishing human-writ...
arXiv AI
Jul 22
ChainMark: Model-Free LLM Watermarking with Closed-Form Calibration
arXiv:2607. 18445v1 Announce Type: cross Abstract: Regulatory regimes such as the EU AI Act mandate machine-readable marking of synthetic text, but existing watermark detectors rely on the generating LM and on heuristic thresholds with no closed-form calibration.
arXiv Machine Learning
Sep 22
On the Information-Theoretic Limits of Latent-Space Watermarking Through Pretrained Generators
The paper investigates latent‑space watermarking using pretrained generators, where a watermark encoder selects latent inputs based on a message and secret key to produce outputs with a specified conditional distribution. For finite alphabets, it derives inner and outer bounds on the rate–key trade‑off and characterizes the capacity region when the generator’s output uniquely determines the latent distribution. The study extends to jointly Gaussian models, identifies key sufficient statistics, optimally allocates secret‑key resources across modes, and analyzes robustness against regeneration attacks, providing compound capacity results and decay rates for repeated attacks.