conftrace_

student-generated output

2 papers

Explore in graph

Also known as

SGO

Co-occurring keywords · papers mentioning both

knowledge distillation (2) instruction-following task (1) speedups (1) off-policy approach (1) skew kullback-leibler divergence (1) large language model (1) instruction-following dataset (1) teacher model (1) student model (1) sequence generation (1)

Papers

SWITCH: Studying with Teacher for Knowledge Distillation of Large Language Models NAACL 2025 DistiLLM: Towards Streamlined Distillation for Large Language Models ICML 2024