Yitian Gong, Luozhijie Jin, Kuangwei Chen, Dong Zhang, Ruifan Deng, Xiaogui Yang, Xin Zhang, Zhaoye Fei, Qinyuan Cheng, Shimin Li, Xipeng Qiu. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Kullback-Leibler (KL) divergence regularization is essential for stabilizing reinforcement learning from human feedback (RLHF) in large language models (LLMs), yet its exact computation requires summing over vocabularies of all tokens, incurring prohibitive memory costs during training.Existing stochastic estimators circumvent this bottleneck by estimating KL divergence using only the sampled token from the trajectory, but suffer from high variance (k 1 ) or systematic bias (k 2 ).We propose TIKE (Top-k Importance-weighted KL Estimator), which exploits the Zipfian structure of language model distributions: by deterministically integrating over only the top-k tokens, TIKE captures most of the probability mass while effectively reducing memory cost.To ensure correctness in off-policy settings characteristic of Group Relative Policy Optimization (GRPO), we incorporate importance sampling weights that correct for distribution shift between rollout and optimization policies.Experiments on models across diverse benchmarks demonstrate that TIKE consistently outperforms stochastic baselines, while exhibiting substantially lower gradient variance.Our analysis reveals that TIKE closely tracks the exact Rao-Blackwellized estimator with nearzero variance, offering a practical path toward stable, memory-efficient KL regularization for reasoning-intensive LLMs training.Code: