---
title: "LAND: Learning an Adaptive Number of Draws for Bayesian Best-of-N Selection"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.03388v1"
permalink: "https://feed.astralor.com/items/itm_e95ff4feb0ec35f32b54ceb2"
published: "2026-11-02T16:26:35.000Z"
score: 57
channel: "tech"
tags: ["RAG","LAND","Learning","Adaptive Number","Draws","Bayesian Best-of-N Selection","Best-of-N"]
---

# LAND: Learning an Adaptive Number of Draws for Bayesian Best-of-N Selection

## At a glance

Best-of-N decoding improves generation quality by sampling multiple candidates and selecting the best, but it allocates equal compute to sources regardless of how much they benefit from additional sampling: the expected…

## Key points

- Best-of-N decoding improves generation quality by sampling multiple candidates and selecting the best, but it allocates equal compute to sources regardless of how much they benefit from additional sampling: the expected…
- To address this shortcoming, we propose LAND (Learning an Adaptive Number of Draws), which dynamically allocates samples according to their posterior-predictive marginal value.
- LAND learns a discrete empirical mixture of source-conditioned score distributions from calibration data, updates its belief about a source as completion scores are observed, and stops sampling when the expected improve…

## Full text

Best-of-N decoding improves generation quality by sampling multiple candidates and selecting the best, but it allocates equal compute to sources regardless of how much they benefit from additional sampling: the expected benefit is small for sources with low-variance score distributions and potentially much larger for those with high-variance distributions. To address this shortcoming, we propose LAND (Learning an Adaptive Number of Draws), which dynamically allocates samples according to their posterior-predictive marginal value. LAND learns a discrete empirical mixture of source-conditioned score distributions from calibration data, updates its belief about a source as completion scores are observed, and stops sampling when the expected improvement of another draw falls below a shared compute price. Across machine-translation experiments with multiple models and language pairs, LAND achieves better MetricX scores than fixed best-of-N at matched average compute. Conversely, at matched translation quality, LAND requires approximately 20-40% fewer candidate generations. Adaptive allocation therefore provides a simple way to retain the benefits of best-of-N while substantially improving its compute efficiency.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_e95ff4feb0ec35f32b54ceb2