BriefGPT.xyz
Nov, 2024
填补空白的提示增强代码辅助的数学推理能力
Gap-Filling Prompting Enhances Code-Assisted Mathematical Reasoning
HTML
PDF
Mohammad Ghiasvand Mohammadkhani
TL;DR
本研究解决了大型语言模型(LLMs)在数学推理中应用受限于计算需求和专有限制的问题。通过创新的填补空白提示(GFP)方法,在解决过程中识别并填补问题空白,从而提高小型语言模型(SLMs)的数学推理能力。实验结果显示,GFP显著提升了SLMs的数学推理能力,具有重要的应用潜力。
Abstract
Despite the strong performance of large
Language Models
(LLMs) in tasks like
Mathematical Reasoning
, their practical use is limited by high computational demands and proprietary restrictions. Chain-of-thought (Co
→