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.
Related event: New SPP Method Aligns Model Values via Pretraining(2 posts)→
More from Research
- Quiz: Double the Residual Stream from 4096 to 8192 — How Does Param Count Change? — Sauers_ · 2026-10-16
- Researcher credits GPT for multiple accepted papers, incl. disproving Wegner's 1965 conjecture — ctjlewis · 2026-10-16
- Open-source shopper attention heatmap: YOLO11-pose + Gaze-LLE + Depth Anything V2 — claudioe · 2026-10-16
- AutoAgent0: VLM-powered agentic runtime lifts long-tail driving success by 28.3pp — yining_hong · 2026-10-16
- Shuffled labels hit AUC 0.59: selection bias, not signal, drives prosody benchmarks — maier_ak · 2026-10-16
- CODESTRUCT reframes codebases as AST action spaces to fix brittle LLM code agents — burkov · 2026-10-16