arXiv AI July 22, 2026 By Chengheng Li-Chen, Kyuhee Kim

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

llms

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.

By Chih-Duo Hong, Yen-Pang Chen, Fang Yu

llms rag benchmarks

arXiv AI

Jun 2

Linguistics-Aware Non-Distortionary LLM Watermarking

arXiv:2606. 00613v1 Announce Type: cross Abstract: Watermarking should identify language-model output without degrading quality or limiting verification to the model provider.

By Shinwoo Park, Hyejin Park, Hyeseon An, Yo-Sub Han

llms computer-vision nlp

arXiv Computation and Language

4d ago

CORE-BREW: LLR-Based Soft Decoding for Robust Multi-Bit LLM Watermarking

CORE-BREW is a new multi‑bit watermarking method for large language models that uses log‑likelihood ratios for soft‑decision decoding, targeting a fixed hit rate to calibrate the watermark channel. It introduces entropy‑aware erasures to reduce perturbations in low‑entropy contexts and combines likelihood‑based scoring with soft‑decision list decoding to better exploit token‑level reliability. Experiments on open‑source LLMs show that CORE‑BREW improves detection robustness and payload recovery compared to the BREW baseline while keeping false‑positive rates low and maintaining translation quality metrics close to unwatermarked text.

By Joeun Kim, HoEun Kim, Young-Sik Kim

llms rag

Hugging Face Trending Papers

Sep 3

Flip, Don't Shuffle: Watermarking LLMs at the Speed of Inference

We introduce Stateless Bernoulli Watermarking (SBW), a new statistical watermark for Large Language Models that determines green list membership through independent per-token Bernoulli trials. Unlike KGW's vocabulary permutation or SynthID's multi-layer tournament, SBW requires only a single comparison per token against a counter-based random number generator, reducing membership complexity to $O(1)$ and enabling single-kernel execution with zero intermediate allocations.

llms benchmarks

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).

By Jose H. Blanchet, T. Tony Cai, Xiang Li, Hao Liu, Qi Long, Weijie J. Su

llms efficiency

arXiv Machine Learning

Jul 30

Adaptively Robust LLM Monitoring via Activation Watermarking

arXiv:2603. 23171v3 Announce Type: replace-cross Abstract: Providers monitor deployed large language models (LLMs) to detect misuse that they cannot prevent.

By Toluwani Aremu, Daniil Ognev, Samuele Poppi, Nils Lukas

llms fine-tuning benchmarks safety

One email a morning, machine-written

Related stories

Signature filtering: a lightweight enhancement for statistical watermark detection in large language models

Linguistics-Aware Non-Distortionary LLM Watermarking

CORE-BREW: LLR-Based Soft Decoding for Robust Multi-Bit LLM Watermarking

Flip, Don't Shuffle: Watermarking LLMs at the Speed of Inference

Optimal Watermark Localization in Mixed-Source Large Language Model Texts

Adaptively Robust LLM Monitoring via Activation Watermarking