@inproceedings{zhang-etal-2026-catmark,
title = "{CATM}ark: A Context-Aware Thresholding Framework for Robust Cross-Task Watermarking in Large Language Models",
author = "Zhang, YU and
Liu, Shuliang and
Xu, Yang and
Hu, Xuming",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.375/",
pages = "8571--8600",
ISBN = "979-8-89176-459-0",
abstract = "Watermarking algorithms for Large Language Models (LLMs) effectively identify machine-generated content by embedding and detecting hidden statistical features in text. However, such embedding leads to a decline in text quality, especially in low-entropy scenarios where performance needs improvement. Existing methods that rely on entropy thresholds often require significant computational resources for tuning and demonstrate poor adaptability to unknown or cross-task generation scenarios. We propose $\textbf{C}$ontext-$\textbf{A}$ware $\textbf{T}$hreshold watermarking ($\textit{CATMark}$), a novel framework that dynamically adjusts watermarking intensity based on real-time semantic context. $\textit{CATMark}$ partitions text generation into semantic states using logits clustering, establishing context-aware entropy thresholds that preserve fidelity in structured content while embedding robust watermarks. Crucially, it requires no pre-defined thresholds or task-specific tuning. Experiments show $\textit{CATMark}$ improves text quality in cross-tasks without sacrificing detection accuracy."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2026-catmark">
<titleInfo>
<title>CATMark: A Context-Aware Thresholding Framework for Robust Cross-Task Watermarking in Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Y</namePart>
<namePart type="given">U</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuliang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuming</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Watermarking algorithms for Large Language Models (LLMs) effectively identify machine-generated content by embedding and detecting hidden statistical features in text. However, such embedding leads to a decline in text quality, especially in low-entropy scenarios where performance needs improvement. Existing methods that rely on entropy thresholds often require significant computational resources for tuning and demonstrate poor adaptability to unknown or cross-task generation scenarios. We propose Context-Aware Threshold watermarking (CATMark), a novel framework that dynamically adjusts watermarking intensity based on real-time semantic context. CATMark partitions text generation into semantic states using logits clustering, establishing context-aware entropy thresholds that preserve fidelity in structured content while embedding robust watermarks. Crucially, it requires no pre-defined thresholds or task-specific tuning. Experiments show CATMark improves text quality in cross-tasks without sacrificing detection accuracy.</abstract>
<identifier type="citekey">zhang-etal-2026-catmark</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.375/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>8571</start>
<end>8600</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CATMark: A Context-Aware Thresholding Framework for Robust Cross-Task Watermarking in Large Language Models
%A Zhang, Y. U.
%A Liu, Shuliang
%A Xu, Yang
%A Hu, Xuming
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F zhang-etal-2026-catmark
%X Watermarking algorithms for Large Language Models (LLMs) effectively identify machine-generated content by embedding and detecting hidden statistical features in text. However, such embedding leads to a decline in text quality, especially in low-entropy scenarios where performance needs improvement. Existing methods that rely on entropy thresholds often require significant computational resources for tuning and demonstrate poor adaptability to unknown or cross-task generation scenarios. We propose Context-Aware Threshold watermarking (CATMark), a novel framework that dynamically adjusts watermarking intensity based on real-time semantic context. CATMark partitions text generation into semantic states using logits clustering, establishing context-aware entropy thresholds that preserve fidelity in structured content while embedding robust watermarks. Crucially, it requires no pre-defined thresholds or task-specific tuning. Experiments show CATMark improves text quality in cross-tasks without sacrificing detection accuracy.
%U https://aclanthology.org/2026.emnlp-main.375/
%P 8571-8600
Markdown (Informal)
[CATMark: A Context-Aware Thresholding Framework for Robust Cross-Task Watermarking in Large Language Models](https://aclanthology.org/2026.emnlp-main.375/) (Zhang et al., EMNLP 2026)
ACL