Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
Turning large language models into cognitive models
2024-01-16
· ICLR 2024 poster ·
anchor
Findings
IC-1217
LLaMA 65B's token-probability readout fails to capture human decision-making, producing near-chance NLL and no human-like exploration behavior
IC-1218
GPT-4 achieves 59.72% accuracy on choices13k and 80.3% on the horizon task when modeling human decisions