Language models can solve complex reasoning tasks better by learning to generate rationales for their predictions. Often these models know how to solve a task but their auto-regressive decoding nature leads to incorrect results if they start incorrectly. We observe that smaller models in particular when corrected, can solve a task that they would have otherwise struggled with. We demonstrate this phenomenon by using a larger model to guide smaller models, which leads to significantly improved performance (up to +24 points on the GSM8K dataset by 7B models). To assist smaller models in initiating the starting step, we propose QuestCoT, where a smaller model first asks itself how to start, before proceeding with a chain of reasoning. On various multistep mathematical reasoning datasets over multiple smaller models, we show that getting the right start can lead to significant performance gains across all models (gains of up to +6 points on GSM8K, +9 on SVAMP, +5 on ASDiv, and +7 on MultiArith).

翻译：语言模型通过学习生成预测依据，能够更好地解决复杂推理任务。这些模型通常知道如何解决问题，但其自回归解码特性会导致若起始错误则产生错误结果。我们观察到，特别是较小模型在被修正后能够解决原本难以处理的任务。我们通过使用更大模型指导较小模型来证明这一现象，这带来了显著的性能提升（7B模型在GSM8K数据集上最高提升24分）。为帮助较小模型正确起始推理步骤，我们提出QuestCoT方法：较小模型在展开推理链之前，首先询问自身应如何开始。通过在多个较小模型上进行各类多步数学推理数据集的实验，我们证明正确起始能为所有模型带来显著性能提升（GSM8K提升6分，SVAMP提升9分，ASDiv提升5分，MultiArith提升7分）。