AINeutralarXiv – CS AI · 8h ago6/10
🧠
TRACE: Distilling Where It Matters via Token-Routed Self On-Policy Alignment
Researchers introduce TRACE, a novel training method that improves AI model performance by selectively applying different optimization techniques to critical versus routine tokens in reasoning tasks. The approach addresses inefficiencies in standard self-distillation by concentrating training effort on important decision points, achieving 2.76 percentage point improvements over baseline methods while better preserving out-of-distribution generalization.