Saved in:
Bibliographic Details
Main Authors: Cha, Sungmin, Cho, Kyunghyun
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.13111
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909990569115648
author Cha, Sungmin
Cho, Kyunghyun
author_facet Cha, Sungmin
Cho, Kyunghyun
contents Knowledge distillation (KD) is a core component in the training and deployment of modern generative models, particularly large language models (LLMs). While its empirical benefits are well documented -- enabling smaller student models to emulate the performance of much larger teachers -- the underlying mechanisms by which KD improves generative quality remain poorly understood. In this work, we present a minimal working explanation of KD in generative modeling. Using a controlled simulation with mixtures of Gaussians, we demonstrate that distillation induces a trade-off between precision and recall in the student model. As the teacher distribution becomes more selective, the student concentrates more probability mass on high-likelihood regions at the expense of coverage, which is a behavior modulated by a single entropy-controlling parameter. We then validate this effect in a large-scale language modeling setup using the SmolLM2 family of models. Empirical results reveal the same precision-recall dynamics observed in simulation, where precision corresponds to sample quality and recall to distributional coverage. This precision-recall trade-off in LLMs is found to be especially beneficial in scenarios where sample quality is more important than diversity, such as instruction tuning or downstream generation. Our analysis provides a simple and general explanation for the effectiveness of KD in generative modeling.
format Preprint
id arxiv_https___arxiv_org_abs_2505_13111
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Why Knowledge Distillation Works in Generative Models: A Minimal Working Explanation
Cha, Sungmin
Cho, Kyunghyun
Machine Learning
Knowledge distillation (KD) is a core component in the training and deployment of modern generative models, particularly large language models (LLMs). While its empirical benefits are well documented -- enabling smaller student models to emulate the performance of much larger teachers -- the underlying mechanisms by which KD improves generative quality remain poorly understood. In this work, we present a minimal working explanation of KD in generative modeling. Using a controlled simulation with mixtures of Gaussians, we demonstrate that distillation induces a trade-off between precision and recall in the student model. As the teacher distribution becomes more selective, the student concentrates more probability mass on high-likelihood regions at the expense of coverage, which is a behavior modulated by a single entropy-controlling parameter. We then validate this effect in a large-scale language modeling setup using the SmolLM2 family of models. Empirical results reveal the same precision-recall dynamics observed in simulation, where precision corresponds to sample quality and recall to distributional coverage. This precision-recall trade-off in LLMs is found to be especially beneficial in scenarios where sample quality is more important than diversity, such as instruction tuning or downstream generation. Our analysis provides a simple and general explanation for the effectiveness of KD in generative modeling.
title Why Knowledge Distillation Works in Generative Models: A Minimal Working Explanation
topic Machine Learning
url https://arxiv.org/abs/2505.13111