PaperScope
LIVE · 2026-09-29 05:40 UTC

How Reusable Are Benchmarks with Richer Feedback?

Youssef Allouah, John Duchi

Latestcs.CLcs.LGcs.AIcs.CV
arXiv ID
2609.32109 v1
Category
Submitted
2026-09-26

Abstract

We study whether benchmarks reliably guide model selection as developers adapt to evaluation feedback across multiple criteria. We find that the worst-case test-set size needed to estimate the best score among $k$ adaptively chosen models, under any convex combination of the criteria, grows exponentially with the number of criteria, reaching the $Θ(\sqrt{k})$ cost of answering $k$ adaptive statistical queries with only $O(\log k)$ criteria, at fixed accuracy and confidence. In attacks on multi-task large language model benchmarks with five to ten criteria, feedback restricted to nondominated task profiles produces large reused-to-held-out score gaps and frequent false winners. These results challenge a prominent explanation for prior observed reliable benchmark reuse---that developers mainly respond to convincing improvements over the current best---in rich-feedback settings, while leaving open how often ordinary model development encounters this vulnerability.

arXiv abs page · PDF · same-day batch