[2301.10226] A Watermark for Large Language Models

Skip to main content

arXiv is now an independent nonprofit!<br>Learn more<br>&times;

Search arXiv

Press Enter to search &middot; Advanced search

-->

Computer Science > Machine Learning

arXiv:2301.10226 (cs)

[Submitted on 24 Jan 2023 (v1), last revised 1 May 2024 (this version, v4)]

Title:A Watermark for Large Language Models

Authors:John Kirchenbauer, Jonas Geiping, Yuxin Wen, Jonathan Katz, Ian Miers, Tom Goldstein<br>View a PDF of the paper titled A Watermark for Large Language Models, by John Kirchenbauer and 5 other authors

View PDF<br>HTML (experimental)

Abstract:Potential harms of large language models can be mitigated by watermarking model output, i.e., embedding signals into generated text that are invisible to humans but algorithmically detectable from a short span of tokens. We propose a watermarking framework for proprietary language models. The watermark can be embedded with negligible impact on text quality, and can be detected using an efficient open-source algorithm without access to the language model API or parameters. The watermark works by selecting a randomized set of "green" tokens before a word is generated, and then softly promoting use of green tokens during sampling. We propose a statistical test for detecting the watermark with interpretable p-values, and derive an information-theoretic framework for analyzing the sensitivity of the watermark. We test the watermark using a multi-billion parameter model from the Open Pretrained Transformer (OPT) family, and discuss robustness and security.

Comments:<br>13 pages in the main body. Published at ICML 2023. Code is available at this http URL

Subjects:

Machine Learning (cs.LG); Computation and Language (cs.CL); Cryptography and Security (cs.CR)

Cite as:<br>arXiv:2301.10226 [cs.LG]

(or<br>arXiv:2301.10226v4 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2301.10226

Focus to learn more

arXiv-issued DOI via DataCite

Submission history<br>From: John Kirchenbauer [view email]<br>[v1]<br>Tue, 24 Jan 2023 18:52:59 UTC (3,550 KB)

[v2]<br>Fri, 27 Jan 2023 18:54:34 UTC (3,620 KB)

[v3]<br>Tue, 6 Jun 2023 17:50:01 UTC (3,618 KB)

[v4]<br>Wed, 1 May 2024 22:04:31 UTC (3,825 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled A Watermark for Large Language Models, by John Kirchenbauer and 5 other authors<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

cs.LG

next >

new<br>recent<br>| 2023-01

Change to browse by:

cs<br>cs.CL<br>cs.CR

References & Citations

NASA ADS<br>Google Scholar

Semantic Scholar

3 blog links<br>(what is this?)

export BibTeX citation<br>Loading...

BibTeX formatted citation

&times;

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?)

IArxiv recommender toggle

IArxiv Recommender<br>(What is IArxiv?)

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? |<br>Disable MathJax (What is MathJax?)

Major funding support from