策略链式思维：通过策略引导提升大语言模型的准确推理能力
Strategic Chain-of-Thought: Guiding Accurate Reasoning in LLMs through Strategy Elicitation
AI总结：
本文提出策略链式思维（SCoT），通过在推理前先引导模型生成问题解决策略，再指导高质量推理路径的生成，在多个推理数据集上显著提升了 LLM 的推理准确率。
摘要：
链式思维（CoT）范式已成为增强大语言模型（LLMs）推理能力的关键方法。然而，尽管 CoT 方法被广泛采用并取得了成功，但由于其无法持续保证所生成推理路径的质量，往往表现出不稳定性，从而导致推理性能欠佳。为应对这一挑战，我们提出了策略链式思维（Strategic Chain-of-Thought，SCoT），这是一种新颖的方法，旨在通过在生成中间推理步骤之前融入策略性知识来提升 LLM 性能。SCoT 在单个提示中采用两阶段方法：首先引导模型提出有效的问题解决策略，然后利用该策略指导生成高质量的 CoT 路径和最终答案。我们在八个具有挑战性的推理数据集上进行了实验，结果表明性能显著提升：使用 Llama3-8b 模型时，在 GSM8K 数据集上提升了 21.05%，在 Tracking_Objects 数据集上提升了 24.13%。此外，我们扩展了 SCoT 框架，开发了一种带有自动匹配示例的少样本方法，取得了更强的结果。这些发现凸显了 SCoT 的有效性，表明其在复杂推理任务中具有大幅提升 LLM 性能的潜力。
英文摘要：
The Chain-of-Thought (CoT) paradigm has emerged as a critical approach for enhancing the reasoning capabilities of large language models (LLMs). However, despite their widespread adoption and success, CoT methods often exhibit instability due to their inability to consistently ensure the quality of generated reasoning paths, leading to sub-optimal reasoning performance. To address this challenge, we propose the \textbf{Strategic Chain-of-Thought} (SCoT), a novel methodology designed to refine LLM performance by integrating strategic knowledge prior to generating intermediate reasoning steps. SCoT employs a two-stage approach within a single prompt: first eliciting an effective problem-solving strategy, which is then used to guide the generation of high-quality CoT paths and final answers. Our experiments across eight challenging reasoning datasets demonstrate significant improvements, including a 21.05\% increase on the GSM8K dataset and 24.13\% on the Tracking\_Objects dataset, respectively, using the Llama3-8b model. Additionally, we extend the SCoT framework to develop a few-shot method with automatically matched demonstrations, yielding even stronger results. These findings underscore the efficacy of SCoT, highlighting its potential to substantially enhance LLM performance in complex reasoning tasks.
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。
