Encyclopedia · 311 concepts
Learn this concept as a feed

Architectures · advanced · concept 96 of 311 · Updated Nov 4, 2026

Knowledge Distillation

Training a smaller 'student' model to mimic a larger 'teacher' model's behavior. The student learns from the teacher's soft outputs (probabilities), capturing knowledge that's lost with hard labels alone.

L7 · LLM and generative AI engineerDevelopersTech leadersQA and testing

Key terms

Teacher modelStudent modelSoft labelsTemperature scaling

Learn these first