Abstract
Knowledge Distillation (KD) has become a cornerstone technique for compressing Large Language Models (LLMs) into smaller, more efficient student models. However, conventional KD approaches typically apply the distillation loss uniformly across all tokens, regardless of the teacher's confidence. This indiscriminate mimicry can introduce noise, as the student is forced to learn from the teacher's uncertain or high-entropy predictions, which may ultimately harm student performance-especially when the teacher is much larger and more powerful. To address this, we propose Speculative Knowledge Distillation (SpecKD), a novel, plug-and-play framework that introduces a dynamic, token-level gating mechanism inspired by the "propose-and-verify" paradigm of speculative decoding. At each step, the student's token proposal is verified against the teacher's distribution; the distillation loss is selectively applied only to "accepted" tokens, while "rejected" tokens are masked out. Extensive experiments on diverse text generation tasks show that SpecKD consistently and significantly outperforms strong KD baselines, leading to more stable training and more capable student models, and achieving state-of-the-art results.
Abstract (translated)
URL
https://arxiv.org/abs/2510.24021
