Large Language Models are Zero-Shot Reasoners

作者： Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, Yusuke Iwasawa (2022)

arXiv： 2205.11916

领域

推理能力

TLDR（中文）

一句 "Let's think step by step" 就能在数学题上把准确率从 ~17% 拉到 ~78%。CoT 能力是模型自带、prompt 触发，这一发现震惊了整个社区。

TLDR (English)

A single phrase "Let's think step by step" boosts math accuracy from ~17% to ~78%. CoT capability is inherent in models, triggered by prompts—this discovery shocked the entire community.

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)
• 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)
• Chain-of-Thought Prompting Elicits Reasoning in Large Language Models Jason Wei 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
• Self-Consistency Improves Chain of Thought Reasoning in Language Models Xuezhi Wang et al. (2022)
  推理能力