Exploring self-distilled reasoning for supervised fine-tuning with Amazon Nova

AWS · 1 month ago · 22

Amazon researchers introduced Self-Distilled Reasoning (SDR), a technique for fine-tuning models that lack reasoning traces by using the base model's own chain-of-thought outputs as training signals. The method recovered mathematical performance from 6 percent back to 70 percent compared to vanilla supervised fine-tuning, while improving target task performance by over 6.5 percent on average. SDR eliminates the need for human annotation, prevents catastrophic forgetting without post-hoc model merging, and enables reasoning capabilities to be preserved during domain-specific customization.