2026
Reward Models Inherit Value Biases from Pretraining
Brian Christian, Jessica A F Thompson, Elle, Vincent Adam, Hannah Rose Kirk, Christopher Summerfield +1
ICLR 2026poster
Reward models (RMs) are central to aligning large language models (LLMs) with human values but have received less attention than pre-trained and post-trained LLMs themselves. Because RMs are initialized from LLMs, they inherit representations that shape their behavior, but the nature and extent of t…