Least-to-Most Prompting Enables Complex Reasoning in Large Language Models

作者： Denny Zhou, Nathanael Schärli, Le Hou, Jason Wei, Nathan Scales, Xuezhi Wang, Dale Schuurmans, Claire Cui, Olivier Bousquet, Quoc Le, Ed Chi (2022)

arXiv： 2205.10625

领域

推理能力

TLDR（中文）

"先把难题拆成易题，再依次解决"是另一条与 CoT 平行的推理范式，对组合泛化任务尤其有效。和 CoT/ToT 一起构成"如何引导大模型分步思考"的三件套。

TLDR (English)

"Break hard problems into easy ones, solve sequentially" is another reasoning paradigm parallel to CoT, especially effective for compositional generalization. Together with CoT/ToT forms the trio of "how to guide LLM step-by-step thinking".

出现在这些文章里

• 提示工程：与模型对话的艺术
• Prompt Engineering: The Art of Talking to Models

同被引用

这些论文与本文出现在同一篇文章中

• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning DeepSeek-AI (2025)
• Large Language Models are Zero-Shot Reasoners Takeshi Kojima et al. (2022)
• Let's Verify Step by Step Hunter Lightman et al. (2023)
• Self-Consistency Improves Chain of Thought Reasoning in Language Models Xuezhi Wang et al. (2022)

相关论文

同一领域的其他论文

• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning DeepSeek-AI (2025)
  推理能力对齐
• OpenAI o1 System Card OpenAI (2024)
  推理能力安全
• Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters Charlie Snell et al. (2024)
  推理能力推理
• Let's Verify Step by Step Hunter Lightman et al. (2023)
  推理能力评估
• Tree of Thoughts: Deliberate Problem Solving with Large Language Models Shunyu Yao et al. (2023)
  推理能力应用
• Large Language Models are Zero-Shot Reasoners Takeshi Kojima et al. (2022)
  推理能力