SDMPrune combines a self-distillation loss with Taylor-based importance scoring to prune only MLP neurons, improving zero-shot performance of compressed LLaMA models over existing pruning methods.
BoolQ: Exploring the surprising difficulty of natural yes/no questions
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
dataset 1polarities
use dataset 1representative citing papers
citing papers explorer
-
SDMPrune: Self-Distillation MLP Pruning for Efficient Large Language Models
SDMPrune combines a self-distillation loss with Taylor-based importance scoring to prune only MLP neurons, improving zero-shot performance of compressed LLaMA models over existing pruning methods.