SelfzCoT: a Self-Prompt Zero-shot CoT from Semantic-level to Code-level for a Better Utilization of LLMs
share
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 with MultiArith from 79.3 SingleEq from 78.70 from 63.70 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 92.39 79.90 performance on GSM8K among all the recent zero-shot methods.
READ FULL TEXT