Silviu Pitis, Michael R. Zhang, Andrew Wang, Jimmy Ba
TL;DR我们提出了一种基于提示集成的方法来进一步提高语言模型推理性能,并在 GSM8k 和 AQuA 数据集上的实验中验证了该方法的优越性。
Abstract
Methods such as chain-of-thought prompting and self-consistency have pushed
the frontier of language model reasoning performance with no additional
training. To further improve performance, we propose a prompt ensemblin