Predicting Human-Gain Curves under Local Proxy Optimization from Repeated Ratings

arXiv cs.AINovember 2, 2026en

arXiv cs.AI

AI Global Wire

arXiv:2610.41114v1 Announce Type: new Abstract: Optimizing a proxy objective can improve human-perceived quality, but the resulting gain can vary with optimization strength. Average proxy-human correlation alone does not reveal how human-perceived quality changes as optimization strength increases. We propose PACE (Proxy Alignment and Curvature Expansion), a pre-optimization diagnostic that uses repeated human ratings to predict the human-gain curve induced by a fixed proxy. The method models proxy optimization as a KL-regularized exponential tilt. At KL radius $d$, the local gain is approximated by $A\sqrt{d}+Bd$, where $A$ measures first-order proxy-human alignment and $B$ captures the lea

This is a short summary published by AI Global Wire. The full article is owned and hosted by arXiv cs.AI — open it there to read it in full.

• Verktyg
• Forskning