Adversarial Moment-Matching Distillation of Large Language Models
This work addresses the computational and memory efficiency challenges in deploying large language models, offering an incremental improvement over existing distillation methods.
The paper tackled the problem of knowledge distillation for large language models by proposing an adversarial moment-matching method to minimize the imitation gap between teacher and student models, achieving new state-of-the-art performance in instruction-following and task-specific experiments.
Knowledge distillation (KD) has been shown to be highly effective in guiding a student model with a larger teacher model and achieving practical benefits in improving the computational and memory efficiency for large language models (LLMs). State-of-the-art KD methods for LLMs mostly rely on minimizing explicit distribution distance between teacher and student probability predictions. Instead of optimizing these mandatory behaviour cloning objectives, we explore an imitation learning strategy for KD of LLMs. In particular, we minimize the imitation gap by matching the action-value moments of the teacher's behavior from both on- and off-policy perspectives. To achieve this action-value moment-matching goal, we propose an adversarial training algorithm to jointly estimate the moment-matching distance and optimize the student policy to minimize it. Results from both task-agnostic instruction-following experiments and task-specific experiments demonstrate the effectiveness of our method and achieve new state-of-the-art performance.