Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
The Reversal Curse: LLMs trained on “A is B” fail to learn “B is A”
2024-01-16
· ICLR 2024 poster ·
anchor
Findings
IC-824
GPT-3 models of all sizes (350M to 175B) can reverse name-description associations in-context with near-perfect accuracy, showing the reversal curse is a property of training rather than reasoning