arXiv Machine Learning
Constitution-Guided Watermarking
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Sep 11
Watermarks Without Verification: AI Text Watermarking After the EU AI Act
The paper discusses the EU AI Act’s requirement for generative AI providers to embed detectable watermarks in their outputs, noting that Anthropic’s Claude models and Google’s Gemini use SynthID‑Text by default. It critiques the lack of verifiability of claims about watermark quality, privacy, and robustness, and evaluates the open‑source SynthID‑Text implementation on two open‑weight models, finding minimal impact on prose and modest correctness loss on code. The authors argue that the real governance issue is the inability to verify these assertions and outline necessary steps—such as output release, configuration disclosure, accredited audits, shared evaluation protocols, and interoperable detection—to address the gaps.
arXiv AI
Oct 15
SkillMarker: A KGW-Based Watermarking Method for Agent Skill Ownership Verification
arXiv:2610.15725v2 Announce Type: cross Abstract: Agent skills encode operational procedures and domain expertise as reusable knowledge assets, yet their distribution in plaintext exposes them to una...
arXiv Machine Learning
Sep 30
AutoMark: Enabling Autoresearch to Discover Better LLM Watermarks
arXiv:2609.37310v1 Announce Type: cross Abstract: With LLM watermarking being deployed commercially and now required by regulations, improving its reliability and effectiveness has become crucial. Ye...
arXiv Computation and Language
6d ago
Watermarkability: Measuring and Improving Language-Model Compatibility with Logit-Based Watermarks
The paper introduces "watermarkability," a metric that quantifies how compatible a language model is with a logit‑based watermark that boosts the probability of a specified token set during decoding. By measuring the expected minimum KL divergence needed to achieve a target probability mass, the authors can assess and compare models and watermark rules. They propose a two‑stage approach—first training a low‑rank adapter conditioned on the target set, then applying a minimal uniform logit bias—to reduce this cost, achieving significant perplexity reductions across multiple watermark schedules on OPT‑125M and Qwen3‑8B.
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
2d ago
MarkTune: Improving the Quality-Detectability Trade-off in Model-Embedded LLM Watermarking
MarkTune is a model‑embedded watermarking framework that improves the trade‑off between generation quality and detectability. By regularizing toward a high‑quality reference distribution, it decouples quality preservation from proximity to the base model and uses the GaussMark detection statistic as a reward during on‑policy fine‑tuning. Empirical results show that MarkTune enhances the quality‑detectability frontier, maintains downstream task performance, and remains robust against text‑editing and open‑weight attacks across diverse datasets.