Chain of Thoughts (CoT)

Introduced in this research paper, chain-of-thought (CoT) prompting enables complex reasoning by introducing intermediate reasoning steps. You can combine it with few-shot prompting to get better results on more complex tasks that require reasoning before responding.

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: 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.

Keep in mind that the authors claim that this is an emergent ability that arises with sufficiently large language models.

Zero-shot COT Prompting

One idea is zero-shot CoT, which essentially involves adding Let's think step by step to the original 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, you started with 10 apples.
You gave away 2 apples to the neighbor and 2 to the repairman, so you had 6 apples left.
Then you bought 5 more apples, so now you had 11 apples.
Finally, you ate 1 apple, so you would remain with 10 apples.

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. This research paper proposes an approach to eliminate manual efforts by leveraging LLMs with a "Let's think step by step" prompt to generate reasoning chains for demonstrations one by one. This automated process can still result in mistakes in the generated chains. To mitigate the effects of the mistakes, the diversity of demonstrations matters. This work proposes Auto-CoT, which samples diverse questions and generates reasoning chains to construct demonstrations.

Auto-CoT consists of two main stages:

Stage 1: question clustering: partition questions of a given dataset into a few clusters
Stage 2: 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 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.

The process is illustrated below:

Code for Auto-CoT is available here.