AI & ML
SOTA or Luck? The Winner's Curse in LLM Leaderboards
arXiv stat.ML0 views
arXiv:2611.22227v1 Announce Type: cross Abstract: Public LLM leaderboards guide model evaluation and adoption, yet the reported performance of top-ranked models can be systematically overstated. This leaderboard winner's curse arises because ranking noisy benchmark scores rewards sampling luck alongside genuine ability. The same selection effect can distort scores throughout the leaderboard, a phenomenon we call the rank-induced bias. We develop an $m$-out-of-$N$ bootstrap to correct for this bias. It assumes a fixed model pool with independent, identically distributed bounded tasks while allowing arbitrary within-task correlation among models. Under exact population tiers separated by positive gaps, we prove that the bootstrap reduces $\Theta(N^{-1/2})$ ranking bias to expected residual bias $o(N^{-1/2})$. Across 14 benchmarks from 5 benchmark families, the rank-1 adjustments range from approximately 0.09 to 3.86 percentage points. In our SWE-bench Verified snapshot, the tied leaders receive an adjustment of 0.90 percentage points. Such overstatement is large enough to make the apparent winner statistically fragile. Thus, we use the same bootstrap to further quantify the intervals of plausible rank positions for each model and group models into tiers. We establish sufficient conditions for consistent recovery of population tiers. On SWE-bench Verified, this procedure places 13 of 173 models in the leading tier. We combine the score adjustment and rank intervals in the Rank Uncertainty and Leaderboard Evaluation Report (RULER). We validate its finite-sample performance using sample splitting and calibrated simulations, and advocate publishing RULER alongside raw rankings so readers can assess both reported performance and the precision of the ordering. RULER also provides guidance for benchmark design that accounts for selection effects and ranking uncertainty.
Source:https://arxiv.org/abs/2611.22227Related posts

The Download: AI learns to smell and hydropower struggles
0MIT Technology Review

Nvidia isn’t selling any more AI chips to China
0The Verge
Nvidia clarifies when it will — and won’t —keep financing neoclouds
0TechCrunch

Google Home speakers get a major Gemini upgrade ‘soon,’ but only for paid subscribers
09to5Google

NVIDIA's CEO Shake-Up Exposes a Costly Prediction Market Deadline
0HackerNoon
Lumi-4B AI Model: Everything You Need to Know
0HackerNoon