Papers › Improving Your Model Ranking on Chatbot Arena by Vote Rigging

Improving Your Model Ranking on Chatbot Arena by Vote Rigging

29 Jan 2025arXiv:2501.17858archive 2025-07-28

Rui Min, Tianyu Pang, Chao Du, Qian Liu, Minhao Cheng, Min Lin

Chatbot Arena is a popular platform for evaluating LLMs by pairwise battles, where users vote for their preferred response from two randomly sampled anonymous models. While Chatbot Arena is widely regarded as a reliable LLM ranking leaderboard, we show that crowdsourced voting can be rigged to improve (or decrease) the ranking of a target model mₜ. We first introduce a straightforward target-only rigging strategy that focuses on new battles involving mₜ, identifying it via watermarking or a binary classifier, and exclusively voting for mₜ wins. However, this strategy is practically inefficient because there are over $190$ models on Chatbot Arena and on average only about 1% of new battles will involve mₜ. To overcome this, we propose omnipresent rigging strategies, exploiting the Elo rating mechanism of Chatbot Arena that any new vote on a battle can influence the ranking of the target model mₜ, even if mₜ is not directly involved in the battle. We conduct experiments on around $1.7$ million historical votes from the Chatbot Arena Notebook, showing that omnipresent rigging strategies can improve model rankings by rigging only hundreds of new votes. While we have evaluated several defense mechanisms, our findings highlight the importance of continued efforts to prevent vote rigging. Our code is available at https://github.com/sail-sg/Rigging-ChatbotArena.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

sail-sg/rigging-chatbotarena officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Chatbot

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections