Prompting methods play a crucial role in enhancing the capabilities of
pre-trained large language models (LLMs). We explore how contrastive prompting
(CP) significantly improves the ability of large language models to perform
complex reasoning. We demonstrate that LLMs are decent contrastive reasoners by
simply adding "Let's give a correct and a wrong answer." before LLMs provide
answers. Experiments on two large language models show that zero-shot
contrastive prompting improves performance on a range of arithmetic,
commonsense, and symbolic reasoning tasks without any hand-crafted few-shot
examples, such as increasing the accuracy on GSM8K from 35.9% to 88.8% and
AQUA-RAT from 41.3% to 62.2% with the state-of-the-art GPT-4 model. Our method
not only surpasses zero-shot CoT and few-shot CoT in most arithmetic and
commonsense reasoning tasks but also can seamlessly integrate with existing
prompting methods, resulting in improved or comparable results when compared to
state-of-the-art methods. Our code is available at
this https URL

对比提示（CP）显著提高了大语言模型在复杂推理方面的能力。零 - shot 对比提示在算术、常识和符号推理任务上提升了性能，无需手动设计少数训练示例，与当前最先进的 GPT-4 模型相比，在 GSM8K 的准确率从 35.9% 提升至 88.8%，在 AQUA-RAT 的准确率从 41.3% 提升至 62.2%。该方法不仅在大多数算术和常识推理任务上超过了零 - shot CoT 和少数 - shot CoT，还能与现有的提示方法无缝集成，得到改进或相当的结果。