Prompt engineering is a relatively new discipline for developing and optimizing prompts to efficiently use language models (LMs) for a wide variety of applications and research topics. Prompt engineering skills help to better understand the capabilities and limitations of large language models (LLMs). Researchers use prompt engineering to improve the capacity of LLMs on a wide range of common and complex tasks such as question answering and arithmetic reasoning. Developers use prompt engineering to design robust and effective prompting techniques that interface with LLMs and other tools.
This guide covers the basics of standard prompts to provide a rough idea on how to use prompts to interact and instruct large language models (LLMs).
All examples are tested with `text-davinci-003` (using OpenAI's playground) unless otherwise specified. It uses the default configurations, e.g., `temperature=0.7` and `top-p=1`.
You can already achieve a lot with prompts, but the quality of results depends on how much information you provide it. A prompt can contain information like the `instruction` or `question` you are passing to the model and including other details such as `inputs` or `examples`.
The sky is blue on a clear day. On a cloudy day, the sky may be gray or white.
```
As you can see, the language model outputs a continuation of strings that make sense give the context `"The sky is"`. The output might be unexpected or far from the task we want to accomplish.
This basic example also highlights the necessity to provide more context or instructions on what specifically we want to achieve.
Is that better? Well, we told the model to complete the sentence so the result looks a lot better as it follows exactly what we told it to do ("complete the sentence"). This approach of designing optimal prompts to instruct the model to perform a task is what's referred to as **prompt engineering**.
The example above is a basic illustration of what's possible with LLMs today. Today's LLMs are able to perform all kinds of advanced tasks that range from text summarization to mathematical reasoning to code generation.
When working with prompts, you will be interacting with the LLM via an API or directly. You can configure a few parameters to get different results for your prompts.
**Temperature** - In short, the lower the temperature the more deterministic the results in the sense that the highest probable next token is always picked. Increasing temperature could lead to more randomness encouraging more diverse or creative outputs. We are essentially increasing the weights of the other possible tokens. In terms of application, we might want to use lower temperature for something like fact-based QA to encourage more factual and concise responses. For poem generation or other creative tasks it might be beneficial to increase temperature.
**Top_p** - Similarly, with top_p, a sampling technique with temperature called nucleus sampling, you can control how deterministic the model is at generating a response. If you are looking for exact and factual answers keep this low. If you are looking for more diverse responses, increase to a higher value.
The general recommendation is to alter one not both.
Before starting with some basic examples, keep in mind that your results may vary depending on the version of LLM you are using.
We have tried a very simple prompt above. A standard prompt has the following format:
```
<Question>?
```
This can be formatted into a QA format, which is standard in a lot of QA dataset, as follows:
```
Q: <Question>?
A:
```
Given the standard format above, one popular and effective technique to prompting is referred to as few-shot prompting where we provide exemplars. Few-shot prompts can be formatted as follows:
```
<Question>?
<Answer>
<Question>?
<Answer>
<Question>?
<Answer>
<Question>?
```
And you can already guess that its QA format version would look like this:
```
Q: <Question>?
A: <Answer>
Q: <Question>?
A: <Answer>
Q: <Question>?
A: <Answer>
Q: <Question>?
A:
```
Keep in mind that it's not required to use QA format. The format depends on the task at hand. For instance, you can perform a simple classification task and give exemplars that demonstrate the task as follows:
Few-shot prompts enable in-context learning which is the ability of language models to learn tasks given only a few examples. We will see more of this in action in the upcoming guides.
---
## Elements of a Prompt
As we cover more and more examples and applications that are possible with prompt engineering, you will notice that there are certain elements that make up a prompt.
A prompt can contain any of the following components:
**Instruction** - a specific task or instruction you want the model to perform
**Context** - can involve external information or additional context that can steer the model to better responses
**Input Data** - is the input or question that we are interested to find a response for
**Output Indicator** - indicates the type or format of output.
Not all the components are required for a prompt and the format depends on the task at hand. We will touch on more concrete examples in upcoming guides.
As you get started with designing prompts, you should keep in mind that it is really an iterative process that requires lot of experimentation to get optimal results. Using a simple playground like OpenAI's or Cohere's is a good starting point.
You can start with simple prompts and keep adding more elements and context as you aim for better results. Versioning your prompt along the way is vital for this reason. As we read the guide you will see many examples where specificity, simplicity, and conciseness will often give you better results.
When you have big task that involves many different subtasks, you can try to break down the task into simpler subtasks and keep building up as you get better results. This avoids adding too much complexity to the prompt design process at the beginning.
You can design effective prompts for various simple tasks by using commands to instruct the model what you want to achieve such as "Write", "Classify", "Summarize", "Translate", "Order", etc.
Keep in mind that you also need to experiment a lot so see what works best. Trying different instructions with different keywords, context, and data and see what works best for your particular use case and task. Usually, the more specific and relevant the context is to the task you are trying to perform, the better. We will touch on the importance of sampling and adding more context in the upcoming guides.
Others recommend that instructions are placed at the beginning of the prompt. It's also recommended that some clear separator like "###" is used to separate the instruction and context.
For instance:
*Prompt:*
```
### Instruction ###
Translate the text below to Spanish:
Text: "hello!"
```
*Output:*
```
¡Hola!
```
### Specificity
Be very specific about the instruction and task you want the model to perform. The more descriptive and detailed the prompt is, the better the results. This is particularly important when you have a desired outcome or style of generation you are seeking. There aren't specific tokens or keywords that lead to better results. It's more important to have a good format and descriptive prompt. In fact, providing examples in the prompt is very effective to get desired output in specific formats.
When designing prompts you should also keep in mind the length of the prompt as there are limitations regarding how long this can be. Thinking about how specific and detailed you should be is something to consider. Too many unnecessary details in not necessarily a good approach. The details should be relevant and contribute to the task at hand. This is something you will need to experiment with a lot. We encourage a lot of experimentation and iteration to optimize prompts for your applications.
As an example, let's try a simple prompt to extract specific information from a piece of text.
*Prompt:*
```
Extract the name of places in the following text.
Desired format:
Place: <comma_separated_list_of_company_names>
Input: "Although these developments are encouraging to researchers, much is still a mystery. “We often have a black box between the brain and the effect we see in the periphery,” says Henrique Veiga-Fernandes, a neuroimmunologist at the Champalimaud Centre for the Unknown in Lisbon. “If we want to use it in the therapeutic context, we actually need to understand the mechanism.""
```
*Output:*
```
Place: Champalimaud Centre for the Unknown, Lisbon
```
Input text is obtained from [this Nature article](https://www.nature.com/articles/d41586-023-00509-z).
### Avoid Impreciseness
Given the tips above about being detailed and improving format, it's easy to fall into the trap of wanting to be too clever about prompts and potentially creating imprecise descriptions. It's often better to be specific and direct. The analogy here is very similar to effective communication -- the more direct, the more effective the message gets across.
Explain the concept prompt engineering. Keep the explanation short, only a few sentences, and don't be too descriptive.
```
It's not clear from the prompt above how many sentences to use and what style. You might still somewhat get good responses with the above prompts but the better prompt would be one that is very specific, concise, and to the point. Something like:
```
Use 2-3 sentences to explain the concept of prompt engineering to a high school student.
Another common tip when designing prompts is to avoid saying what not to do but say what to do instead. This encourages more specificity and focus on the details that lead to good responses from the model.
Here is an example of movie recommendation chatbot failing at exactly what I don't want it to do because of how I wrote the instruction -- focusing on what not to do.
*Prompt:*
```
The following is an agent that recommends movies to a customer. DO NOT ASK FOR INTERESTS. DO NOT ASK FOR PERSONAL INFORMATION.
Customer: Please recommend a movie based on my interests.
Agent:
```
*Output:*
```
Sure, I can recommend a movie based on your interests. What kind of movie would you like to watch? Do you prefer action, comedy, romance, or something else?
```
Here is a better prompt:
*Prompt:*
```
The following is an agent that recommends movies to a customer. The agent is responsible to recommend a movie from the top global trending movies. It should refrain from asking users for their preferences and avoid asking for personal information. If the agent doesn't have a movie to recommend, it should respond "Sorry, couldn't find a movie to recommend today.".
Customer: Please recommend a movie based on my interests.
Agent:
```
*Output:*
```
Sorry, I don't have any information about your interests. However, here's a list of the top global trending movies right now: [list of movies]. I hope you find something you like!
```
Some of the examples above were adopted from the ["Best practices for prompt engineering with OpenAI API" article.](https://help.openai.com/en/articles/6654000-best-practices-for-prompt-engineering-with-openai-api)
