SAAS: Solving Ability Amplification Strategy for Enhanced Mathematical Reasoning in Large Language Models

arXiv:2404.03887v1 Announce Type: new
Abstract: This study presents a novel learning approach designed to enhance both mathematical reasoning and problem-solving abilities of Large Language Models (LLMs). We focus on integrating the Chain-of-Thought (CoT) and the Program-of-Thought (PoT) learning, hypothesizing that prioritizing the learning of mathematical reasoning ability is helpful for the amplification of problem-solving ability. Thus, the initial learning with CoT is essential for solving challenging mathematical problems. To this end, we propose a sequential learning approach, named SAAS (Solving …

abstract arxiv cs.ai cs.cl focus language language models large language large language models llms mathematical reasoning novel problem-solving reasoning saas strategy study thought type