面向大型语言模型的水印优化

Computer Science > Cryptography and Security arXiv:2312.17295 (cs) [Submitted on 28 Dec 2023 (v1), last revised 23 Sep 2026 (this version, v2)] Title:Optimizing watermarks for large language models Authors:Bram Wouters View a PDF of the paper titled Optimizing watermarks for large language models, by Bram Wouters View PDF HTML (experimental) Abstract:With the rise of large language models (LLMs) and concerns about potential misuse, watermarks for generative LLMs have recently attracted much attention. An important aspect of such watermarks is the trade-off between their identifiability and their impact on the quality of the generated text. This paper introduces a systematic approach to this trade-off in terms of a multi-objective optimization problem. For a large class of robust, efficient watermarks, the associated Pareto optimal solutions are identified and shown to outperform the currently default watermark. Comments: Subjects: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Computation and Language (cs.CL) Cite as: arXiv:2312.17295 [cs.CR] (or arXiv:2312.17295v2 [cs.CR] for this version) https://doi.org/10.48550/arXiv.2312.17295 Focus to learn more arXiv-issued DOI via DataCite Journal reference: Proceedings of the 41st International Conference on Machine Learning (ICML), PMLR 235:53251-53269, 2024 Related DOI: https://doi.org/10.5555/3692070.3694252 Focus to learn more DOI(s) linking to related resources Submission history From: Bram Wouters [view email] [v1] Thu, 28 Dec 2023 16:10:51 UTC (2,161 KB) [v2] Wed, 23 Sep 2026 10:39:26 UTC (2,477 KB) Full-text links: Access Paper: View a PDF of the paper titled Optimizing watermarks for large language models, by Bram Wouters View PDF HTML (experimental) TeX Source view license Current browse context: cs.CR new | recent | 2023-12 Change to browse by: cs cs.AI cs.CL 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?)