[2605.05443] SLAM: Structural Linguistic Activation Marking for Language Models
Skip to main content
Learn about arXiv becoming an independent nonprofit.
We gratefully acknowledge support from the Simons Foundation, member institutions, and all contributors. Donate
> cs > arXiv:2605.05443
Help | Advanced Search
All fields Title Author Abstract Comments Journal reference ACM classification MSC classification Report number arXiv identifier DOI ORCID arXiv author ID Help pages Full text
Search
GO
quick links
Login
Help Pages
About
-->
Computer Science > Computation and Language
arXiv:2605.05443 (cs)
[Submitted on 6 May 2026]
Title:SLAM: Structural Linguistic Activation Marking for Language Models
Authors:Fabrice Harel-Canada, Amit Sahai
View a PDF of the paper titled SLAM: Structural Linguistic Activation Marking for Language Models, by Fabrice Harel-Canada and Amit Sahai
View PDF HTML (experimental)
Abstract:LLM watermarks must be detectable without compromising text quality, yet most existing schemes bias the next-token distribution and pay for detection with measurable quality loss. We present SLAM (Structural Linguistic Activation Marking), a novel white-box watermarking scheme that sidesteps this cost by writing the mark into structural geometry rather than token frequencies: sparse autoencoders identify residual-stream directions encoding linguistic structure (e.g., voice, tense, clause order), and we causally steer those directions at generation time, leaving lexical sampling and semantics unconstrained. On Gemma-2 2B and 9B, SLAM achieves 100% detection accuracy with a quality cost of only 1-2 reward points - compared to 7.5-11.5 for KGW, EWD, and Unigram - with naturalness and diversity preserved at near-unwatermarked levels across both models. The trade-off is a complementary robustness profile: SLAM resists word-level edits but is vulnerable to paraphrase that restructures syntax (at a quality cost), the converse of token-distribution methods.
Comments: 9 pages, under review
Subjects:
Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
Cite as: arXiv:2605.05443 [cs.CL]
(or arXiv:2605.05443v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2605.05443
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Fabrice Harel-Canada [view email] [v1] Wed, 6 May 2026 21:11:17 UTC (369 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled SLAM: Structural Linguistic Activation Marking for Language Models, by Fabrice Harel-Canada and Amit Sahai
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CL
new | recent | 2026-05
Change to browse by:
cs cs.AI
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?)
About
Help
contact arXivClick here to contact arXiv Contact
subscribe to arXiv mailingsClick here to subscribe Subscribe
Copyright
Privacy Policy
Web Accessibility Assistance
arXiv Operational Status