Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
NLPO
anchor
Findings
IC-849
GPT-2 and T5-base exhibit vanishing expected gradients under RFT for inputs with small reward standard deviation, prevalent in 3 of 7 GRUE datasets, causing RFT to underperform SFT
[compared-to]