Basic Prompting

[topaz lake]

Introduce some basic prompting skill

Zero-Shot

Zero-shot Prompting is to simply feed the task text to the model and ask for results.

Prompt:

Classify the text into neutral, negative or positive. 

Text: I think the vacation is okay.
Sentiment:

Output:

Neutral

Few-shot

Few-shot Prompting presents a set of high-quality demonstrations, each consisting of both input and desired output, on the target task. As the model first sees good examples, it can better understand human intention and criteria for what kinds of answers are wanted. Therefore, few-shot learning often leads to better performance than zero-shot. However, it comes at the cost of more token consumption and may hit the context length limit when input and output text are long.

Prompt:

A "whatpu" is a small, furry animal native to Tanzania. An example of a sentence that uses
the word whatpu is:
We were traveling in Africa and we saw these very cute whatpus.

To do a "farduddle" means to jump up and down really fast. An example of a sentence that uses
the word farduddle is:

Output:

When we won the game, we all started to farduddle in celebration.

Prompt:

This is awesome! // Negative
This is bad! // Positive
Wow that movie was rad! // Positive
What a horrible show! //

Output:

Negative

Chain-of-Thought Prompting (CoT)

Chain-of-thought (CoT) prompting generates a sequence of short sentences to describe reasoning logics step by step, known as reasoning chains or rationales, to eventually lead to the final answer. The benefit of CoT is more pronounced for complicated reasoning tasks, while using large models (e.g. with more than 50B parameters). Simple tasks only benefit slightly from CoT prompting.

Few-shot CoT

It is to prompt the model with a few demonstrations, each containing manually written (or model-generated) high-quality reasoning chains.

Prompt:

Question: Tom and Elizabeth have a competition to climb a hill. Elizabeth takes 30 minutes to climb the hill. Tom takes four times as long as Elizabeth does to climb the hill. How many hours does it take Tom to climb up the hill?
Answer: It takes Tom 30*4 = <<30*4=120>>120 minutes to climb the hill.
It takes Tom 120/60 = <<120/60=2>>2 hours to climb the hill.
So the answer is 2.
===
Question: Jack is a soccer player. He needs to buy two pairs of socks and a pair of soccer shoes. Each pair of socks cost $9.50, and the shoes cost $92. Jack has $40. How much more money does Jack need?
Answer: The total cost of two pairs of socks is $9.50 x 2 = $<<9.5*2=19>>19.
The total cost of the socks and the shoes is $19 + $92 = $<<19+92=111>>111.
Jack need $111 - $40 = $<<111-40=71>>71 more.
So the answer is 71.
===
Question: Marty has 100 centimeters of ribbon that he must cut into 4 equal parts. Each of the cut parts must be divided into 5 equal parts. How long will each final cut be?
Answer:

Output:

Each of the 4 equal parts of the ribbon will be 100/4 = <<100/4=25>>25 centimeters long.  
Each of the 25 centimeter parts must be divided into 5 equal parts, so each final cut will be 25/5 = <<25/5=5>>5 centimeters long.  
So the answer is 5.

Zero-shot CoT

Use natural language statement like Let's think step by step to explicitly encourage the model to first generate reasoning chains and then to prompt with Therefore, the answer is to produce answers. Or a similar statement Let's work this out it a step by step to be sure we have the right answer.