Hybrid Policy Distillation for LLMs
This work addresses the challenge of efficiently distilling knowledge from large language models for researchers and practitioners, though it is incremental as it builds on existing distillation methods.
The paper tackled the problem of compressing large language models via knowledge distillation by proposing Hybrid Policy Distillation (HPD), which integrates forward and reverse KL divergences and combines off-policy data with on-policy sampling, resulting in improved optimization stability, computational efficiency, and performance across math reasoning, dialogue, and code tasks.
Knowledge distillation (KD) is a powerful paradigm for compressing large language models (LLMs), whose effectiveness depends on intertwined choices of divergence direction, optimization strategy, and data regime. We break down the design of existing KD methods and present a unified view that establishes connections between them, reformulating KD as a reweighted log-likelihood objective at the token level. We further propose Hybrid Policy Distillation (HPD), which integrates the complementary advantages of forward and reverse KL to balance mode coverage and mode-seeking, and combines off-policy data with lightweight, approximate on-policy sampling. We validate HPD on long-generation math reasoning as well as short-generation dialogue and code tasks, demonstrating improved optimization stability, computational efficiency, and final performance across diverse model families and scales. The code related to this work is available at https://github.com/zwhong714/Hybrid-Policy-Distillation.