来源：https://www.promptingguide.ai/techniques/cot 爬取日期：2026-03-22

Chain-of-Thought Prompting

Introduced in Wei et al. (2022), chain-of-thought (CoT) prompting enables complex reasoning capabilities through intermediate reasoning steps. You can combine it with few-shot prompting to get better results on more complex tasks that require reasoning before responding.

Few-Shot CoT Prompting

Prompt:

The odd numbers in this group add up to an even number: 4, 8, 9, 15, 12, 2, 1.
A: Adding all the odd numbers (9, 15, 1) gives 25. The answer is False.

The odd numbers in this group add up to an even number: 17, 10, 19, 4, 8, 12, 24.
A: Adding all the odd numbers (17, 19) gives 36. The answer is True.

The odd numbers in this group add up to an even number: 16, 11, 14, 4, 8, 13, 24.
A: Adding all the odd numbers (11, 13) gives 24. The answer is True.

The odd numbers in this group add up to an even number: 17, 9, 10, 12, 13, 4, 2.
A: Adding all the odd numbers (17, 9, 13) gives 39. The answer is False.

The odd numbers in this group add up to an even number: 15, 32, 5, 13, 82, 7, 1.
A:

Output:

Adding all the odd numbers (15, 5, 13, 7, 1) gives 41. The answer is False.

Wow! We can see a perfect result when we provided the reasoning step. In fact, we can solve this task by providing even fewer examples, i.e., just one example seems enough:

The results show strong performance even with minimal examples, suggesting the technique requires “sufficiently large language models.”

Zero-Shot CoT Prompting

One recent idea that came out more recently is the idea of zero-shot CoT (Kojima et al. 2022) that essentially involves adding “Let’s think step by step” to the original prompt. Let’s try a simple problem and see how the model performs:

Prompt:

I went to the market and bought 10 apples. I gave 2 apples to the neighbor and 2 to the repairman. I then went and bought 5 more apples and ate 1. How many apples did I remain with?

Output:

11 apples

The answer is incorrect! Now let’s try with the special prompt.

Prompt:

I went to the market and bought 10 apples. I gave 2 apples to the neighbor and 2 to the repairman. I then went and bought 5 more apples and ate 1. How many apples did I remain with?

Let's think step by step.

Output:

First, I started with 10 apples.
I gave away 2 apples to the neighbor and 2 to the repairman, so I had 6 apples left.
Then I bought 5 more apples, so now I had 11 apples.
Finally, I ate 1 apple, so I was left with 10 apples.

It’s impressive that this simple prompt is effective at this task. This is particularly useful where you don’t have too many examples to use in the prompt.

Automatic Chain-of-Thought (Auto-CoT)

When applying chain-of-thought prompting with demonstrations, the process involves hand-crafting effective and diverse examples. This manual effort could lead to suboptimal solutions. Zhang et al. (2022) propose an approach to eliminate manual efforts by leveraging LLMs with “Let’s think step by step” prompt to generate reasoning chains for demonstrations one by one. This automatic process can still end up with mistakes in generated chains. To mitigate the effects of the mistakes, the diversity of demonstrations matter. This works proposes Auto-CoT, which samples questions with diversity and generates reasoning chains to construct the demonstrations.

Auto-CoT consists of two main stages:

Question clustering: partition questions of a given dataset into a few clusters
Demonstration sampling: select a representative question from each cluster and generate its reasoning chain using Zero-Shot-CoT with simple heuristics

The simple heuristics could be like length of questions (e.g., 60 tokens) and number of steps in rationale (e.g., 5 reasoning steps). This encourages the model to use simple and accurate demonstrations.