Complementing reinforcement learning with SFT through logit averaging in the post training of LLMs
Year: 2026
Type: preprint
Abstract: We introduce a novel method that averages the logits of a frozen reference policy (e.g., SFT) and a trainable policy, and incorporate the method into Group Relative Policy Optimization (GRPO). In contrast to Reinforcement Learning with Verifiable Rewards (RLVR) methods, our proposal does not involve a Kullback Leibler (KL) regularization or critic; the trainable policy and the reference anchor are coupled through the logit averaging structure to leverage the reasoning expertise of the trainable policy while maintaining the formatting advantage of SFT. Our method is evaluated on MATH, cn-k12, and MMLU, and the results show a higher accuracy or at least comparable accuracy relative to the canonical KL-regularized GRPO.
Source: arXiv (Cornell University)
Authors: Gan, Xingwei, Zhu, Ying
Institution: University of California San Diego
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7161964568
Cites:
Cited by:
Related to: