Replacing AdamW with IVON and pruning 10% of highest-variance LoRA parameters improves average commonsense-reasoning accuracy by 1.3 points and calibration by 5.4 points on Llama-3.2-3B.
BitFit: Simple parameter-efficient fine-tuning for transformer-based masked language-models
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.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Improving LoRA with Variational Learning
Replacing AdamW with IVON and pruning 10% of highest-variance LoRA parameters improves average commonsense-reasoning accuracy by 1.3 points and calibration by 5.4 points on Llama-3.2-3B.