Learning to Maximize Mutual Information for Chain-of-Thought Distillation

arXiv:2403.03348v1 Announce Type: new
Abstract: Knowledge distillation, the technique of transferring knowledge from large, complex models to smaller ones, marks a pivotal step towards efficient AI deployment. Distilling Step-by-Step (DSS), a novel method utilizing chain-of-thought (CoT) distillation, has demonstrated promise by imbuing smaller models with the superior reasoning capabilities of their larger counterparts. In DSS, the distilled model acquires the ability to generate rationales and predict labels concurrently through a multi-task learning framework. However, DSS overlooks the intrinsic relationship between …

abstract ai deployment arxiv capabilities cs.ai cs.cl deployment distillation information knowledge marks novel pivotal reasoning step-by-step thought type