大型语言模型的增强型提示集成（英文版）

英文标题：Boosted Prompt Ensembles for Large Language Models中文摘要：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。英文摘要：Methods such as chain-of-thought prompting and self-consistency have pushedthe frontier of language model reasoning performance with no additionaltraining. To further improve performance, we propose a prompt ensembling methodfor large language models, which uses a small dataset to construct a set of fewshot prompts that together comprise a ``boosted prompt ensemble''