跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2610.19095 · v3

Similar Models, Broken Odds: Where Luce's Axiom Fails in Chatbot Arena

首次提交 2026-10-14 03:33
版本更新 2026-11-13 12:17
雷达观测 2026-11-17 04:57
arXiv ↗PDF ↗

摘要

Chatbot Arena gives each language model one Bradley-Terry score, which fixes how often any model should beat any other. Choice theory predicts where this fails: near-copies are compared on the few details in which they differ, so votes between them are more decisive than their scores imply, exactly for the comparison a lab cares about, a new version against the old one. On 1.8 million Arena votes, votes between versions of one model are 1.37 times as decisive as Bradley-Terry predicts, between sizes of one generation 1.26 times and between models of one lab 1.12 times; a release a year later points the same way, and the effect survives tie, prompt, topic and timing checks. How alike two models' answers are worded and formatted tracks the effect. Plain scores leave the odds between relatives about 9% too close to even on held-out votes; a correction with four to six parameters roughly halves this and predicts held-out votes better, mostly by modeling ties, while the leaderboard order barely moves; frozen and carried to new releases, its gains in head-to-head odds are too small for our test to establish. With language-model judges and three-answer menus, a near-copy takes votes mostly from its twin when choices are pooled over prompts (log-odds shift +0.10, 95% interval 0.05 to 0.16), less so within a prompt.

作者备注:20 pages, 5 figures, 10 tables; v3: adds a test on human summarization preferences and a calculation of votes needed for a release decision; clearer abstract, introduction and transfer results; appendix regrouped

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

本站首次收录为 v3,暂无更早版本可对照。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v3 · 2026-11-13 12:17 · 最新观测版本

Similar Models, Broken Odds: Where Luce's Axiom Fails in Chatbot Arena

Chatbot Arena gives each language model one Bradley-Terry score, which fixes how often any model should beat any other. Choice theory predicts where this fails: near-copies are compared on the few details in which they differ, so votes between them are more decisive than their scores imply, exactly for the comparison a lab cares about, a new version against the old one. On 1.8 million Arena votes, votes between versions of one model are 1.37 times as decisive as Bradley-Terry predicts, between sizes of one generation 1.26 times and between models of one lab 1.12 times; a release a year later points the same way, and the effect survives tie, prompt, topic and timing checks. How alike two models' answers are worded and formatted tracks the effect. Plain scores leave the odds between relatives about 9% too close to even on held-out votes; a correction with four to six parameters roughly halves this and predicts held-out votes better, mostly by modeling ties, while the leaderboard order barely moves; frozen and carried to new releases, its gains in head-to-head odds are too small for our test to establish. With language-model judges and three-answer menus, a near-copy takes votes mostly from its twin when choices are pooled over prompts (log-odds shift +0.10, 95% interval 0.05 to 0.16), less so within a prompt.

查看此版本解读 →查看此版本原文 ↗