Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
Understanding prompt engineering may not require rethinking generalization
2024-01-16
· ICLR 2024 poster ·
anchor
Findings
IC-1105
PAC-Bayes generalization bounds for discrete class prompts on CLIP are within a few percentage points of the actual test error across CIFAR-10, CIFAR-100, ImageNet, FMOW, and OfficeHome
IC-1106
CLIP prompts found by greedy search do not fit random labels: train and test error drop in tandem as the fraction of flipped labels increases, unlike a linear probe which achieves near-random accuracy