Symbolic Chain-of-Thought Distillation: Small Models Can Also "Think" Step-by-Step

arXiv:2306.14050v2 Announce Type: replace
Abstract: Chain-of-thought prompting (e.g., "Let's think step-by-step") primes large language models to verbalize rationalization for their predictions. While chain-of-thought can lead to dramatic performance gains, benefits appear to emerge only for sufficiently large models (beyond 50B parameters). We show that orders-of-magnitude smaller models (125M -- 1.3B parameters) can still benefit from chain-of-thought prompting. To achieve this, we introduce Symbolic Chain-of-Thought Distillation (SCoTD), a method to train a smaller student model on rationalizations sampled from a significantly …

abstract arxiv benefits beyond cs.cl distillation language language models large language large language models large models orders parameters performance predictions prompting show small step-by-step think thought type