OFA tunes LayerNorm parameters as optimization preconditioners and adds step-ratio and sharpness penalties, reporting consistent few-shot accuracy gains over baselines on Llama and GPT-2 models.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Optimization-Inspired Few-Shot Adaptation for Large Language Models
OFA tunes LayerNorm parameters as optimization preconditioners and adds step-ratio and sharpness penalties, reporting consistent few-shot accuracy gains over baselines on Llama and GPT-2 models.