arXiv Machine Learning August 17, 2026 By Nghia T. Le, Alan Ritter, Kartik Goyal

Semantic Differentiation for Tackling Challenges in Watermarking Low-Entropy Constrained Generation Outputs

Read the original on arXiv Machine Learning →

arXiv:2601. 11629v2 Announce Type: replace-cross Abstract: We demonstrate that while the current approaches for language model watermarking are effective for open-ended generation, they are inadequate at watermarking LM outputs for constrained generation tasks with low-entropy output spaces.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jul 8

Beyond Heuristic Tuning: Power-Calibrated LLM Watermarking

arXiv:2607. 05694v1 Announce Type: cross Abstract: Logit-based watermarking is a widely used mechanism for identifying LLM generated content, yet its effectiveness is governed by a fundamental trade-off between detectability and semantic distortion.

By Xiaopu Wang, Zelin He, Chengyuan Liu, Runze Li

llms

arXiv AI

Jul 29

AGMark: Attention-Guided Dynamic Watermarking for Large Vision-Language Models

arXiv:2602. 09611v2 Announce Type: replace-cross Abstract: Watermarking has emerged as a pivotal solution for content traceability and intellectual property protection in large vision language models (LVLMs).

By Yue Li, Xin Yi, Dongsheng Shi, Yongyi Cui, Gerard de Melo, Linlin Wang

llms multimodal

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 16

SAMark: A Self-Anchored Text Watermarking with Paragraph-Level Paraphrase Robustness

arXiv:2605. 25796v2 Announce Type: replace-cross Abstract: Semantic-level watermarking (SWM) improves robustness against text modifications by treating sentences as the basic unit.

By Jiahao Huo, Wenjie Qu, Yibo Yan, Kening Zheng, Jiaheng Zhang, Xuming Hu, Philip S. Yu, Mingxun Zhou

arXiv AI

Aug 10

WorldMark: A Plug-and-Play World Knowledge Interface for Cross-Host Language Model Watermarking

arXiv:2608. 06416v1 Announce Type: cross Abstract: Watermarking traces the provenance of text produced by large language models by embedding statistically detectable signals during decoding.

By Song Xiao, Yuqi Yuan, Yanshuo Zhang, Kejun Zhang

llms rag

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

Related stories

Beyond Heuristic Tuning: Power-Calibrated LLM Watermarking

AGMark: Attention-Guided Dynamic Watermarking for Large Vision-Language Models

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

SAMark: A Self-Anchored Text Watermarking with Paragraph-Level Paraphrase Robustness

WorldMark: A Plug-and-Play World Knowledge Interface for Cross-Host Language Model Watermarking

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