works on
counterfactual analysis 1multimodal distillation 1on-policy learning 1target reconstruction 1visual attribution 1

From the 1 of 5 linked papers with an AI index.

collaborators
Showing cs.CLShow all

1 paper · 1 filter

cs.CL2025

Direct Preference Knowledge Distillation for Large Language Models

Yixing Li, Yuxian Gu, Li Dong +3

In the field of large language models (LLMs), Knowledge Distillation (KD) is a critical technique for transferring capabilities from teacher models to student models. However, exis…