Can Small Language Models Help Large Language Models Reason Better?: LM-Guided Chain-of-Thought

Understand

We introduce a novel framework, LM-Guided CoT, that leverages a lightweight (i.e., <1B) language model (LM) for guiding a black-box large (i.e., >10B) LM in reasoning tasks.

• Specifically, the lightweight LM first generates a rationale for each input instance.
• The Frozen large LM is then prompted to predict a task output based on the rationale generated by the lightweight LM.
• Our approach is resource-efficient in the sense that it only requires training the lightweight LM.