kojima2022-zeroshot-cot

arXiv: 2205.11916

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.

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。