This paper show a work on better use of LLMs with SelfzCoT a self-prompt zero-shot CoT. Specifically, on the zero-shot arithmetic reasoning tasks, the accuracy of the proposed SelfzCoT is improved with GSM8K from 40.50% to 82.34%, with MultiArith from 79.3% to 94.7%, with ADDSUB from 74.70% to 94.10%, with SingleEq from 78.70% to 91.30%, with AQUA from 31.90% to 82.33%, and with SVAMP from 63.70% to 79.70%. Totally, using the first two lasting path activations to LLM and particularly, the code-level self-prompt, the SelfzCoT has a huge improvement on all six zero-shot arithmetic reasoning tasks. Additionally, our modified zero-shot CoT (MzCoT) also achieves remarkable performance in the reasoning tasks. The accuracy of the proposed MzCoT is enhanced with GSM8K from 40.50% to 76.32%, with MultiArith from 79.3% to 96.97%, with ADDSUB from 74.70% to 92.39%, with SingleEq from 78.70% to 94.60%, with AQUA from 31.90% to 79.90%, and with SVAMP from 63.70% to 81.50%. Notably, SelfzCoT has the best performance on GSM8K among all the recent zero-shot methods.

翻译：本文展示了利用SelfzCoT（一种自提示零样本思维链方法）更好地使用大语言模型（LLMs）的工作。具体而言，在零样本算术推理任务中，所提出的SelfzCoT在GSM8K上的准确率从40.50%提升至82.34%，MultiArith上从79.3%提升至94.7%，ADDSUB上从74.70%提升至94.10%，SingleEq上从78.70%提升至91.30%，AQUA上从31.90%提升至82.33%，SVAMP上从63.70%提升至79.70%。总体而言，通过使用前两个持续路径激活作用于LLM，特别是代码级自提示，SelfzCoT在所有六个零样本算术推理任务上均获得了巨大提升。此外，我们改进的零样本思维链方法（MzCoT）在推理任务中也取得了显著性能。所提出的MzCoT在GSM8K上的准确率从40.50%提升至76.32%，MultiArith上从79.3%提升至96.97%，ADDSUB上从74.70%提升至92.39%，SingleEq上从78.70%提升至94.60%，AQUA上从31.90%提升至79.90%，SVAMP上从63.70%提升至81.50%。值得注意的是，在所有近期零样本方法中，SelfzCoT在GSM8K上取得了最佳性能。