Statistical Rejection Sampling Improves Preference Optimization

Improving the alignment of language models with human preferences remains an active research challenge. Previous approaches have primarily utilized online Reinforcement Learning from Human Feedback (RLHF). Recently, offline methods such as Sequence Likelihood Calibration (SLiC) and Direct Preference Optimization (DPO) have emerged as attractive alternatives, offering improvements in stability and scalability while maintaining competitive performance. SLiC refines its loss function using sequence pairs sampled from a supervised fine-tuned (SFT) policy, while DPO directly optimizes language models based on preference data, foregoing the need for a separate reward model. However, the maximum likelihood estimator (MLE) of the target optimal policy requires labeled preference pairs sampled from that policy. The absence of a reward model in DPO constrains its ability to sample preference pairs from the optimal policy. Meanwhile, SLiC can only sample preference pairs from the SFT policy. To address these limitations, we introduce a novel approach called Statistical Rejection Sampling Optimization (RSO) designed to source preference data from the target optimal policy using rejection sampling, enabling a more accurate estimation of the optimal policy. We also propose a unified framework that enhances the loss functions used in both SLiC and DPO from a preference modeling standpoint. Through extensive experiments across diverse tasks, we demonstrate that RSO consistently outperforms both SLiC and DPO as evaluated by both Large Language Models (LLMs) and human raters.