How Do Humans Write Code? Large Models Do It the Same Way Too

arXiv:2402.15729v1 Announce Type: cross
Abstract: Large Language Models (LLMs) often make errors when performing numerical calculations. In contrast to traditional chain-of-thought reasoning, the program-of-thoughts approach involves generating executable code to solve problems. By executing this code, it achieves more precise results. Using generated executable code instead of natural language can reduce computational errors. However, we observe that when LLMs solve mathematical problems using code, they tend to generate more incorrect reasoning than when using natural language. To address this issue, …

abstract arxiv code contrast cs.ai cs.cl cs.pl errors generated humans language language models large language large language models large models llms numerical reasoning results solve thought thoughts type