用多样提示策略扩大搜索空间，提升大模型数学推理效率。
Expanding Search Space with Diverse Prompting Agents: An Efficient Sampling Approach for LLM Mathematical Reasoning
- 融合多种提示方法，均匀采样拓展解题路径
- 在MATH-hard数据集上少用43%运行次数达最优解
- 适合追求高效推理的LLM应用开发者
大型语言模型在复杂任务如数学推理中表现出色。然而，传统方法过度依赖单一提示策略的一致性，限制了多样化解题思路的探索。本研究通过实验分析不同提示方法在数学推理领域的表现，发现每种方法探索的搜索空间各不相同，且问题越复杂，差异越显著。为此，我们设计了一种高效的采样机制，均匀结合来自多种方法的样本，不仅扩大了最大搜索空间，还在更少运行次数下实现更高性能。特别是在MATH数据集中的难题子集MATH-hard上，平均仅需比单一方法少43%的运行次数即可达到最大搜索空间。结果表明，整合多样化解题策略对增强大模型推理能力至关重要。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have exhibited remarkable capabilities in many complex tasks including mathematical reasoning. However, traditional approaches heavily rely on ensuring self-consistency within single prompting method, which limits the exploration of diverse problem-solving strategies. This study addresses these limitations by performing an experimental analysis of distinct prompting methods within the domain of mathematical reasoning. Our findings demonstrate that each method explores a distinct search space, and this differentiation becomes more evident with increasing problem complexity. To leverage this phenomenon, we applied efficient sampling process that uniformly combines samples from these diverse methods, which not only expands the maximum search space but achieves higher performance with fewer runs compared to single methods. Especially, within the subset of difficult questions of MATH dataset named MATH-hard, The maximum search space was achieved while utilizing approximately 43% fewer runs than single methods on average. These findings highlight the importance of integrating diverse problem-solving strategies to enhance the reasoning abilities of LLMs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。