SOURCE-LINKED INTELLIGENCE

ExpBoN: Exponential-Noise Best-of-$n$ for Efficient Test-Time LLM Alignment

arXiv · AI, language, vision and robotics · article · Sep 18, 2026 · UTC

Best-of-$n$ (BoN) sampling is a simple yet effective inference-time alignment method, but hard maximization provides only coarse control over the trade-off between reward and distribution shift. Soft Best-of-$n$ (Verdun et al. 2025) provides smoother control and converges to the optimal distribution associated with KL-regularized reward maximization. In this paper, we introduce ExpBoN, an alternative soft BoN method based on the exponential-noise report-noisy-max mechanism. It admits an exact finite-$n$ decomposition, which yields exponentially fast convergence in total variation, expected rew

Read original source ↗ Open in workspace

recordType

paper

region

Global