Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
MQP
anchor
Findings
IC-1088
ICL predictions in LLaMA, LLaMA-2, and Falcon models depend on in-context label information and can learn truly novel label relationships
[eval]
IC-1089
ICL in LLaMA, LLaMA-2, and Falcon models cannot fully overcome pre-training label preferences when in-context labels are flipped
[eval]