Prompt Engineering Fundamentals

Imagine having a super smart helper that can write perfect sentences, create different kinds of writing, translate languages, and answer your questions really well.

These helpers are called large language models (LLMs). LLMs are like giant libraries filled with information from the internet. But instead of looking for a specific book, you just give them a question or a task.

This is where prompt engineering comes in. It's like giving the LLM the right instructions to get the best results. By using prompt engineering, you can make the LLM do a lot of work for you and get really good answers.

Crafting the perfect prompt

Now, let's get down to business! One of the quickest and best ways to learn how to craft the perfect prompt is to consider the common mistakes people make.

Listed below are a few common mistakes that people usually make while writing prompts:

• Being too vague: Don't expect an LLM to read your mind. Vague prompts lead to vague responses.
• Grammatical goofs: Typos and grammatical errors can confuse the LLM and lead to nonsensical results. Double-check your prompt before hitting enter.
• Asking leading questions: Want an unbiased answer? Avoid phrasing your prompt in a way that steers the LLM towards a specific response.

Avoiding these common mistakes still might not give you the most refined output. Therefore, it is good to follow some best practices that have been determined experimentally by the members of LLM communities.

• Start with a clear objective: What exactly do you want the LLM to achieve?
• Provide context: The more context you give, the better the LLM can understand your request.
• Use a conversational tone: Treat the LLM like a helpful assistant, not a complex machine.
• Refine and iterate: Don't be afraid to experiment and adjust your prompt based on the results you receive.

Prompt Templates

There are various ways to write a prompt. No matter what method you use, the instructions and the intent must be clear.

A prompt template includes some combination of these elements:

• Task
• Goal
• Action
• Problem
• Outcome
• Role
• Format
• Input
• Steps
• Expectation
• Context
• Elaboration

The following infographic that I created shows a few ways to write prompts that convey the instructions and intent clearly to the LLM. Each template caters to a different scenario and writing style.

Understanding zero-shot, one-shot and few-shot prompting

Prompts are instructions that you give to an AI model to perform a specific task. These prompts can range from simple requests to complex commands.

The number of examples that you provide in the prompt can significantly influence the model's performance.

A zero-shot prompt is one that does not provide any examples. For example, "Write a poem about a robot who wants to be a chef."

A one-shot prompt is one that provides a single example. For example, "Translate 'Hello, how are you?' into French."

A few-shot prompt is one that provides multiple examples. For example, "Translate the following sentences: 'I like dogs.' 'She is beautiful.'

'They are eating pizza.'"

Why do we use these different types of prompts?

• Zero-shot prompts test the model's general knowledge and ability to understand instructions without specific examples.

• One-shot prompts assess the model's ability to learn from a single example and apply it to new situations.

• Few-shot prompts evaluate the model's ability to learn from multiple examples and generalize its knowledge to new tasks.

Making LLMs “think”

Using these different types of prompts and different prompting techniques we can make LLMs think, improving their responses and reducing the abstraction.

Let’s review one of the most popular prompting techniques, the chain-of-thought (CoT) prompting technique. In simpler terms, this means using a few examples to teach the LLM to think out loud and explain its reasoning before giving the final answer. This helps us understand how the LLM arrived at its conclusion and can also help improve its accuracy.

The following is an example of a one-shot chain-of-thought prompt:

Q: Jack has two bags, each containing three apples. How many apples does Jack have in total?
A: One bag contains 3 apples, so two bags contain 3 * 2 = 6 apples.
Q: {QUESTION}
A:

This CoT technique can also be effective in prompt decomposition which means breaking a complex problem (prompt) into simple smaller problems (tasks) using the right set of prompts.

Similarly, there exists a concept of prompt aggregation which acts like an ensemble module. It is the process of using multiple prompts to solve the same problem, then aggregating these responses into a final output. In many cases, a majority vote selecting the most frequent response is used to generate the final output.

Both prompt decomposition and prompt aggregation techniques help to reduce the variance of LLM outputs and often improve the accuracy of responses, but both techniques come with the cost of increasing the number of model calls needed to reach a final answer.

Summary and next steps

This article introduced you to communicating with large language models (LLMs) by teaching you the fundamentals of prompt engineering. You learned how prompts guide these models, and how to avoid common pitfalls to get the best results. The prompt templates can help kickstart your LLM adventures.

If you're ready to dive in to do some prompt engineering using these prompting techniques, check out this tutorial series, "Use various models with the watsonx.ai flows engine." Or, check out using watsonx Prompt Lab in this tutorial, "Guiding Llama 2 with prompt engineering by developing system and instruction prompts."