Test-time reward-guided alignment of language models by importance sampling on pre-logit space
About
Test-time alignment of large language models (LLMs) attracts attention because fine-tuning of LLMs requires high computational costs. In this paper, we propose a new test-time reward-guided alignment method called adaptive importance sampling on pre-logits (AISP) on the basis of the sampling-based model predictive control with the stochastic control input. AISP applies the Gaussian perturbation into pre-logits, which are outputs of the penultimate layer, so as to maximize expected rewards with respect to the mean of the perturbation. We demonstrate that the optimal mean is obtained by importance sampling with sampled rewards. AISP outperforms best-of-n sampling in terms of rewards over the number of used samples and achieves higher rewards than other reward-based test-time alignment methods.