Hugging Face Trending Papers September 3, 2026

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

Read the original on Hugging Face Trending Papers →

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.

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 Hugging Face Trending Papers.

arXiv Machine Learning

Sep 4

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

arXiv:2609. 03844v1 Announce Type: cross Abstract: 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.

By Simone Ceppi, Ignacio Sanchez

llms benchmarks

arXiv AI

Jul 16

WaterMoE: Expert-Routing-based Watermarking for High Fidelity and Efficiency

arXiv:2607. 13099v1 Announce Type: cross Abstract: Large language models (LLMs) have achieved remarkable success but raise growing concerns about content provenance and misuse, motivating the need for reliable watermarking techniques.

By Z Sun, Q Jiang, S Sheng, L Xiang

llms efficiency benchmarks

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

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.

By Chengheng Li-Chen, Kyuhee Kim

llms

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

arXiv Machine Learning

Jul 8

Multi-Channel Spread-Spectrum Code Watermarking

arXiv:2607. 06009v1 Announce Type: cross Abstract: Attributing code to the large language model that produced it is essential for provenance, licensing, and misuse accountability, yet no deployed watermark meets this need.

By Soohyeon Choi, Debin Gao, Yue Duan

llms rag

One email a morning, machine-written

Related stories

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

WaterMoE: Expert-Routing-based Watermarking for High Fidelity and Efficiency

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

ChainMark: Model-Free LLM Watermarking with Closed-Form Calibration

Adaptively Robust LLM Monitoring via Activation Watermarking

Multi-Channel Spread-Spectrum Code Watermarking