New Paper: Injecting Synthetic Moral Reflections During Pretraining Shifts Value Priorities in 3B Models

sethlazar · x · 2026-08-14

The Synthetic Persona Pretraining paper is out, proposing to inject synthetic morally-laden reflections into 10% of pretraining documents, training models up to 3B parameters. Early intervention significantly shifts the model's value priorities.

Original post →

More from Research

Research channel →