Text Watermarking

Follow this topic Ask about this topic

Text watermarking studies how to embed signals in language-model outputs so they can be detected later for provenance, attribution, or message recovery. Common approaches bias token probabilities using secret keys, while semantic, structural, and byte-level methods aim to survive paraphrasing, edits, or differences between models; error-correcting codes can help recover longer payloads. Researchers evaluate detection accuracy and false alarms alongside text quality, robustness to attacks, and performance on tasks such as summarization, question answering, and code generation. The central tension is that stronger or more persistent signals can distort output or enable unwanted monitoring, while many current methods remain vulnerable to rewriting and are not yet reliable forensic evidence.

Latest papers

44 papers10 papers in the last four weeks, up 233% on the four weeks before. 0.1% of all new papers.

Every Bit, Everywhere, All at Once: A Binomial Multibit LLM Watermark
May 12, 2026Thibaud Gloaguen, Robin Staab, Mark Vero +1Text Watermarking Multi-Bit Watermarking
ETH Zurich
Detecting Verbatim LLM Copy-Paste in Homework
May 7, 2026Aizierjiang AiersilanText Watermarking AI-Generated Text Detection
The George Washington University
SWAN: Semantic Watermarking with Abstract Meaning Representation
May 5, 2026Ziping Ye, Gourab Dey, Christos Christodoulopoulos +7Text Watermarking LLM Watermarking
1Amazon · 2Information Commissioner’s Office · 3Meta +2
Block-wise Codeword Embedding for Reliable Multi-bit Text Watermarking
May 1, 2026Joeun Kim, HoEun Kim, Dongsup Jin +1Text Watermarking Multi-Bit Watermarking
Department of AI, DGIST, Daegu, Republic of Korea · Department of ICT Convergence, University of Ulsan, Ulsan, Republic of Korea · Department of EECS, DGIST, Daegu, Republic of Korea
QuantileMark: A Message-Symmetric Multi-bit Watermark for LLMs
Apr 15, 2026Junlin Zhu, Baizhou Huang, Xiaojun WanMulti-Bit Watermarking Text Watermarking
Wangxuan Institute of Computer Technology, Peking University
TimeMark: A Trustworthy Time Watermarking Framework for Exact Generation-Time Recovery from AIGC
Apr 14, 2026Shangkun Che, Silin Du, Ge GaoText Watermarking LLM Watermarking
Economics and Management School, Wuhan University, Wuhan, China · School of Economics and Management, Tsinghua University, Beijing, China · School of Business Administration, Southwestern University of Finance and Economics, China
Optimal Multi-bit Generative Watermarking Schemes Under Worst-Case False-Alarm Constraints
Apr 9, 2026Yu-Shin Huang, Chao Tian, Krishna NarayananMulti-Bit Watermarking Text Watermarking
XMark: Reliable Multi-Bit Watermarking for LLM-Generated Texts
Apr 6, 2026Jiahao Xu, Rui Hu, Olivera Kotevska +1Multi-Bit Watermarking Text Watermarking
University of Nevada, Reno · Oak Ridge National Laboratory
Refined Detection for Gumbel Watermarking
Mar 31, 2026Tor LattimoreWatermark Removal Detection Text Watermarking
Google DeepMind
When Only the Final Text Survives: Implicit Execution Tracing for Multi-Agent Auditing
Mar 18, 2026Yi Nian, Haosen Cao, Shenzhe Zhu +4Data Provenance in Language Models AI Agent Auditing
University of Southern California · University of Toronto · University of Illinois Chicago +1
Fast segmentation of watermarked texts from large language models through an epidemic change-point framework
Sep 25, 2025Soham Bonnerjee, Subhrajyoty Roy, Sayar KarmakarText Watermarking LLM Watermarking
University of Chicago · Washington University in St. Louis · University of Florida
Majority Bit-Aware Watermarking For Large Language Models
Aug 5, 2025Jiahao Xu, Rui Hu, Olivera Kotevska +1Multi-Bit Watermarking Text Watermarking
University of Nevada, Reno · Oak Ridge National Laboratory
Optimal Estimation of Watermark Proportions in Hybrid AI-Human Texts
Jun 27, 2025Xiang Li, Garrett Wen, Weiqing He +3Text Watermarking Minimax Estimation
University of Pennsylvania · Yale University
The Feasibility of Topic-Based Watermarking on Academic Peer Reviews
May 27, 2025Alexander Nemecek, Yuzhou Jiang, Erman AydayText Watermarking LLM Watermarking
Case Western Reserve University

May 12, 2026J/K move · Enter open · S save

Every Bit, Everywhere, All at Once: A Binomial Multibit LLM Watermark

Thibaud Gloaguen, Robin Staab, Mark Vero, Martin Vechev

ETH Zurich

Text Watermarking Multi-Bit Watermarking LLM Watermarking Robust Watermarking

Open paper AskPDF arXiv

With LLM watermarking already being deployed commercially, practical applications increasingly require multibit watermarks that encode more complex payloads, such as user IDs or timestamps, into the generated text. In this work, we propose a fundamentally new approach for multibit watermarking: introducing binomial encoding to directly encode every bit of the payload at every token position. We complement our approach with a stateful encoder that during generation dynamically redirects encoding pressure toward underencoded bits. Our evaluation against 8 baselines on up to 64-bit payloads shows that our scheme achieves superior message accuracy and robustness, with the gap to baseline methods widening in more relevant settings (i.e., large payloads and low-distortion regimes). At the same time, we challenge prior works' evaluation metrics, highlighting their lack of practical insights, and introduce per-bit confidence scoring as a practically relevant metric for evaluating multibit LLM watermarks.