Prompt-Engineering-Guide/guides/prompts-advanced-usage.md

Advanced Prompt Usage

By this point, it should be obvious that it helps to improve prompts to get better results on different tasks. That’s the whole idea behind prompt engineering.

While those examples were fun, let’s cover a few concepts more formally before we jump into more advanced concepts.

Chain-of-Thought Prompting

Introduced in Wei et al. (2022), chain-of-thought (CoT) prompting uses few chain of thought demonstrations are provided as exemplars in prompting to improve the ability of large language models to perform complex reasoning.

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 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

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

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.

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.

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