Skip to content
AI News HubLIVE
Original source2 min read

Leaderboard Hacking: Preference-Based Model Evaluations are Vulnerable to Manipulation

Summary

arXiv paper reveals that arena-style leaderboards using Bradley-Terry models are highly vulnerable to strategic voting, prompting, and nomination, which can boost a model's rank by up to 45 places.

SourcearXiv AIAuthor: Eve Fleisig, Joachim Baumann, Dylan Hadfield-Menell, Dirk Hovy
Leaderboard Hacking: Preference-Based Model Evaluations are Vulnerable to Manipulation
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 10 Nov 2026]

Title:Leaderboard Hacking: Preference-Based Model Evaluations are Vulnerable to Manipulation

View a PDF of the paper titled Leaderboard Hacking: Preference-Based Model Evaluations are Vulnerable to Manipulation, by Eve Fleisig and 3 other authors

View PDF HTML (experimental)

Abstract:Arena-style rankings of language models are a widely used evaluation framework in online leaderboards, research papers, and model evaluation in production. These rankings aim to realistically assess model performance using pairwise comparisons of anonymous models on user prompts, aggregating votes via the Bradley-Terry model to produce the final ranking. However, we find that these leaderboards are highly vulnerable to several manipulation strategies that unscrupulous providers could use to boost a model's rank: strategic voting (individual votes that boost a model's rank, including votes on irrelevant models), strategic prompting (choosing prompts that favor a model), and strategic nomination (boosting the rank of a model by inserting irrelevant models). We demonstrate these effects on public leaderboard data, analyze the circumstances that cause these vulnerabilities, and describe approaches to safeguard against each attack. Notably, these issues hold for any preference-based evaluation using the Bradley-Terry model that allows open prompting, voting, or model submission. These manipulations boost the rank of nearly every tested model; each attack can boost a model by up to 15-20 places in a ranking and, combined, they can boost a model by up to 45 places.

Subjects:

Artificial Intelligence (cs.AI)

Cite as: arXiv:2611.14769 [cs.AI]

(or arXiv:2611.14769v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2611.14769

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Eve Fleisig [view email] [v1] Tue, 10 Nov 2026 21:47:55 UTC (2,991 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Leaderboard Hacking: Preference-Based Model Evaluations are Vulnerable to Manipulation, by Eve Fleisig and 3 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.AI

new | recent | 2026-11

Change to browse by:

cs

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

Data provided by:

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?)

Key points and analysis

Article intelligence

InvestorsAdvanced

Key points

  • Three manipulation strategies: strategic voting, strategic prompting, and strategic nomination
  • Each attack can boost a model by 15-20 places; combined attacks can boost by up to 45 places
  • Vulnerabilities affect any preference-based evaluation using Bradley-Terry models with open prompting, voting, or model submission

Highlights and analysis are generated automatically and may contain errors. Check the original source.