When Metropolis and Hastings Meet Bradley and Terry: Exact MCMC From Preference Voting

2026-09-01

AI Summary

本文提出Pref-MH方法，通过利用人类或模型裁判的成对比较来解决生成建模中条件采样问题，而无需直接评估目标密度。

Abstract

Sampling from distributions conditioned on desired semantic properties is an emerging challenge in modern generative modeling. Metropolis-Hastings (MH) provides a principled route to conditional sampling, but requires access to exact pointwise target-density evaluations, which are not available in generative settings. Meanwhile, pairwise comparisons by humans or model "judge" are highly accessible and have proved valuable across diverse applications. We introduce Pref-MH, a general exact MH sampler for judge-induced conditional distributions using only stochastic binary pairwise comparisons. Our key observation is that the MH unnormalized density ratio matches the preference odds of the Bradley-Terry (BT) choice model. The central challenge is that while MH requires precise ratio computation, BT judges provide only sampled binary feedback. To this end, we develop a valid accept/reject rule whose resulting Markov chain provably converges to the target distribution. We further show that, for a fixed proposal kernel and budget, Pref-MH is optimal in the Peskun-Tierney sense among this class of exact reversible acceptance rules. Experiments on text generation and molecular design with LLM judges, as well as image generation with VLM judges, demonstrate that Pref-MH provides a practical and flexible approach to conditional sampling when comparative feedback is relatively easy to obtain.

Problem

• Conditional Sampling
• Metropolis-Hastings
• Preference Voting
• Generative Modeling
• Pairwise Comparisons

Innovation

• Pref-MH
• Conditional Sampling
• Binary Comparisons
• Metropolis-Hastings
• Bradley-Terry Model