SOURCE-LINKED INTELLIGENCE

Privacy Without Regret: Differentially Private Inference-Time Alignment

arXiv · AI, language, vision and robotics · article · Aug 26, 2026 · UTC

Best-of-N (BoN) sampling is the simplest and most widely deployed inference-time alignment strategy, but it suffers from two distinct problems: reward hacking, in which the selected response exploits errors in the proxy reward model, and the absence of any privacy protection for the sensitive human preference data used to train that reward model. We show that a single intervention-adding calibrated noise to reward scores before selection-resolves both. Our first result, Private Best-of-N (PrivBoN), establishes that Gumbel noise at an appropriate scale simultaneously provides $ε$-differential p

Read original source ↗ Open in workspace

recordType

paper

region

Global