Models Learn to Think When Forced to Forget: Digital Metabolism Revealed

According to the paper 'Digital Metabolism: Decoupling Logic from Facts via Regenerative Unlearning' by Mengmeng Peng, Zhenyu Fang, and He Sun, forcing models to unlearn facts (below 7% retention) causes spontaneous Chain-of-Thought emergence. This means we can build modular AI systems where reasoning and knowledge are independently updatable components.