Topic-Based Watermarks for Large Language Models

[2404.02138] Topic-Based Watermarks for Large Language Models Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Cryptography and Security arXiv:2404.02138 (cs) [Submitted on 2 Apr 2024 ( v1 ), last revised 15 Apr 2026 (this version, v6)] Title: Topic-Based Watermarks for Large Language Models Authors: Alexander Nemecek , Yuzhou Jiang , Erman Ayday View a PDF of the paper titled Topic-Based Watermarks for Large Language Models, by Alexander Nemecek and 2 other authors View PDF HTML (experimental) Abstract: The indistinguishability of large language model (LLM) output from human-authored content poses significant challenges, raising concerns about potential misuse of AI-generated text and its influence on future model training. Watermarking algorithms offer a viable solution by embedding detectable signatures into generated text. However, existing watermarking methods often involve trade-offs among attack robustness, generation quality, and additional overhead such as specialized frameworks or complex integrations. We propose a lightweight, topic-guided watermarking scheme for LLMs that partitions the vocabulary into topic-aligned token subsets. Given an input prompt, the scheme selects a relevant topic-specific token list, effectively "green-listing" semantically aligned tokens to embed robust marks while preserving fluency and coherence. Experimental results across multiple LLMs and state-of-the-art benchmarks demonstrate that our method achieves text quality comparable to industry-leading systems and simultaneously improves watermark robustness against paraphrasing and lexical perturbation attacks, with minimal performance overhead. Our approach avoids reliance on additional mechanisms beyond standard text generation pipelines, enabling straightforward adoption and suggesting a practical path toward globally consistent watermarking of AI-generated content. Comments: Accepted at ACL 2026 Findings Subjects: Cryptography and Security (cs.CR) ; Computation and Language (cs.CL); Machine Learning (cs.LG) Cite as: arXiv:2404.02138 [cs.CR] (or arXiv:2404.02138v6 [cs.CR] for this version) https://doi.org/10.48550/arXiv.2404.02138 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Alexander Nemecek [ view email ] [v1] Tue, 2 Apr 2024 17:49:40 UTC (1,661 KB) [v2] Tue, 16 Apr 2024 07:28:05 UTC (1,661 KB) [v3] Mon, 19 Aug 2024 17:16:08 UTC (2,171 KB) [v4] Fri, 7 Feb 2025 22:45:20 UTC (162 KB) [v5] Mon, 2 Mar 2026 21:26:43 UTC (1,481 KB) [v6] Wed, 15 Apr 2026 01:27:38 UTC (1,482 KB) Full-text links: Access Paper: View a PDF of the paper titled Topic-Based Watermarks for Large Language Models, by Alexander Nemecek and 2 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CR < prev | next > new | recent | 2024-04 Change to browse by: cs cs.CL cs.LG References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Optimal Watermark Localization in Mixed-Source Large Language Model Texts#609322
• A Watermark for Large Language Models#16582
• DenMark: Robust Semantic Watermarking for Diffusion Language Models#1083714
• Watermarking Diffusion Language Models#1014549
• Robust Text Watermarking for Large Language Models via Dual Semantic Embeddings#324824