Reward Models Inherit Value Biases from Pretraining ICLR2026
Collection
Reward models for the paper Christian et al., "Reward Models Inherit Value Biases from Pretraining" (ICLR 2026)
•
23 items
•
Updated
Brian Christian
brianchristian
AI & ML interests
None yet
Recent Activity
updated
a collection
3 days ago
Reward Models Inherit Value Biases from Pretraining ICLR2026
updated
a collection
3 days ago
Reward Models Inherit Value Biases from Pretraining ICLR2026
updated
a collection
3 days ago
Reward Models Inherit Value Biases from Pretraining ICLR2026
Organizations
updated
a
collection
3 days ago