EGAD adaptively distills LLM knowledge at the token level by using entropy to create a curriculum from low- to high-entropy tokens, adjust temperature, and switch between logits-only and feature-based branches.
In: ICASSP 2026-2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
EGAD: Entropy-Guided Adaptive Distillation for Token-Level Knowledge Transfer
EGAD adaptively distills LLM knowledge at the token level by using entropy to create a curriculum from low- to high-entropy tokens, adjust temperature, and switch between logits-only and feature-based branches.