[2606.24890] Small edits, large models: How Wikipedia advocacy shapes LLM values

-->

Computer Science > Computation and Language

arXiv:2606.24890 (cs)

[Submitted on 30 Apr 2026]

Title:Small edits, large models: How Wikipedia advocacy shapes LLM values

Authors:Jasmine Brazilek, Maria Navas, Alexa Gnauck<br>View a PDF of the paper titled Small edits, large models: How Wikipedia advocacy shapes LLM values, by Jasmine Brazilek and 2 other authors

View PDF<br>HTML (experimental)

Abstract:Can a small group of volunteers shape how AI systems discuss animal welfare, just by editing Wikipedia? We show that they can. Wikipedia appears in nearly every major language model training dataset and is weighted more heavily than web-crawled text. The Pro-Animal Wikipedians (PAW), a group of advocates who add sourced animal welfare content to relevant articles, have made 125 edits across 115 pages. Using gradient-based data attribution (Bergson; MAGIC), we traced how these edits influence language model behavior. TrackStar retrieval attribution on Llama 3.1 8B found that PAW-edited sections made up 68 percent of the highest-attributed documents for animal welfare queries (p

Subjects:

Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Computers and Society (cs.CY)

Cite as:<br>arXiv:2606.24890 [cs.CL]

(or<br>arXiv:2606.24890v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2606.24890

Focus to learn more

arXiv-issued DOI via DataCite

Submission history<br>From: Jasmine Brazilek [view email]<br>[v1]<br>Thu, 30 Apr 2026 02:18:50 UTC (451 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled Small edits, large models: How Wikipedia advocacy shapes LLM values, by Jasmine Brazilek and 2 other authors<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

cs.CL

next >

new<br>recent<br>| 2026-06

Change to browse by:

cs<br>cs.AI<br>cs.CY

References & Citations

NASA ADS<br>Google Scholar

Semantic Scholar

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?)

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?)