arXiv Computation and Language November 4, 2026 By Hongliang Liu

Constructing Budgeted KGW Evasion through Token-Event Evidence Replacement

Read the original on arXiv Computation and Language →

The paper presents a method for evading Knowledge-Guided Watermarking (KGW) by replacing token‑event evidence with ordinary phrase rewrites. It jointly selects LLM‑proposed alternatives, measures global token‑edit distance, and uses exact coverage search to maximize removal of original scored token pairs within a budget. Experiments on short passages show that about half of detected sources can be rewritten to pass a blinded detector with a moderate token‑edit cost, though the approach does not outperform simpler rewriting strategies.

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 Computation and Language.

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

Aug 18

What Do Compliance Detectors Read? An Audit of Activation Probes and Guard Models

arXiv:2608. 16852v1 Announce Type: new Abstract: Regulatory compliance monitoring in deployed language models is increasingly implemented as a legal and audit control, checking model outputs against written rules spanning data protection, healthcare, financial regulation, and platform policy.

By Saisab Sadhu, Aadit Sengupta, Vinay Kumar Sankarapu, Pratinav Seth

llms benchmarks

arXiv Computation and Language

Oct 19

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.

By Zewei Deng, Mohamed Seif, Liyan Xie

safety

arXiv AI

Sep 1

LLM Judges Verify Presence, Not Absence: Omission Blindness in AI Clinical Notes and What Recovers It

arXiv:2608.31016v1 Announce Type: cross Abstract: Ambient AI scribes draft clinical notes, and published audits find their dominant error is omission: information the encounter established that the n...

By Sebastian Fox, Luke Markham, Ryan Lail, Michael Karotsieris

llms benchmarks

Hugging Face Trending Papers

Oct 6

Semantic Behavioral Watermarking: Paraphrase-Robust and Forgery-Resistant Provenance for LLM Agents

Behavioral watermarking embeds an owner identifier in an LLM agent's high-level action choices, giving provenance without touching output tokens. Prior agent watermarks break in two ways. First, all t...

llms agents benchmarks

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.

By Shuwen Chai, Qiaosen Wang

llms