Anthropic researchers detail "model spec midtraining", which adds a stage between pretraining and fine&tuning to improve generalization from alignment training (Anthropic)
Anthropic: Anthropic researchers detail “model spec midtraining”, which adds a stage between pretraining and fine-tuning to improve generalization from alignment training — Sara Price2, Samuel Marks2,†, Jon Kutasov2,† — 1Anthropic Fellows Program; 2Anthropic; †Equal advising
Anthropic:
Anthropic researchers detail “model spec midtraining”, which adds a stage between pretraining and fine-tuning to improve generalization from alignment training — Sara Price2, Samuel Marks2,†, Jon Kutasov2,† — 1Anthropic Fellows Program; 2Anthropic; †Equal advising