SAAS：用于增强大语言模型数学推理能力的解题能力放大策略
SAAS: Solving Ability Amplification Strategy for Enhanced Mathematical Reasoning in Large Language Models
AI总结：
提出 SAAS 顺序学习策略，通过先 CoT 后 PoT 的训练顺序增强 LLM 的数学推理与解题能力，并在多个基准上达到 SOTA。
摘要：
本研究提出了一种新颖的学习方法，旨在提升大语言模型（LLM）的数学推理和问题解决能力。我们聚焦于整合思维链（CoT）与思维程序（PoT）学习，并假设优先学习数学推理能力有助于放大问题解决能力。因此，使用 CoT 进行初始学习对于解决具有挑战性的数学问题至关重要。为此，我们提出了一种名为 SAAS（Solving Ability Amplification Strategy，解题能力放大策略）的顺序学习方法，该方法策略性地从 CoT 学习过渡到 PoT 学习。我们的实证研究在多个基准上进行了广泛的性能比较，结果表明 SAAS 达到了最先进（SOTA）性能。这些结果强调了该顺序学习方法的有效性，标志着 LLM 数学推理领域的一项重大进展。
英文摘要：
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 Ability Amplification Strategy), which strategically transitions from CoT learning to PoT learning. Our empirical study, involving an extensive performance comparison using several benchmarks, demonstrates that our SAAS achieves state-of-the-art (SOTA) performance. The results underscore the effectiveness of our sequential learning approach, marking a significant advancement in the field of mathematical reasoning in LLMs.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
