先定策略再推理，让大模型更稳定地解决复杂问题
Strategic Chain-of-Thought: Guiding Accurate Reasoning in LLMs through Strategy Elicitation
- 先提取解题策略，再生成推理路径，提升逻辑一致性
- 在GSM8K上提升21.05%，Tracking_Objects上提升24.13%
- 适合需要高可靠推理的数学与逻辑任务
Chain-of-Thought（CoT）已成为提升大语言模型（LLM）推理能力的关键方法。然而，尽管广泛应用且成效显著，传统CoT方法因难以持续保证推理路径质量，常表现出不稳定性。为此，我们提出新型方法——战略链式思维（Strategic Chain-of-Thought, SCoT），通过在单个提示中采用两阶段设计：首先提取有效解题策略，再以此指导高质量推理路径与最终答案的生成。在八个具有挑战性的推理数据集上的实验表明，使用Llama3-8b模型时，SCoT在GSM8K上提升21.05%，在Tracking_Objects上提升24.13%。此外，我们将SCoT扩展为少样本方法，自动匹配示范样本，取得更优效果。结果证实了SCoT的有效性，凸显其在复杂推理任务中显著提升LLM性能的潜力。
原文摘要 · Abstract (English)
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.
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。