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

arXiv:2404.03414v1 Announce Type: new
Abstract: 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. …

abstract arxiv box cs.ai cs.cl framework instance language language model language models large language large language models novel reason reasoning small small language models tasks thought type