Often, the best way to learn concepts is by going through examples. Below we cover a few examples of how well-crafted prompts can be used to perform all types of interesting and different tasks.
One of the standard tasks in natural language generation is text summarization. Text summarization can include many different flavors and domains. One of the most promising applications of language models is the ability to summarize articles and concepts into quick and easy-to-read summaries. Let's try a basic summarization task using prompts.
Antibiotics are a type of medication used to treat bacterial infections. They work by either killing the bacteria or preventing them from reproducing, allowing the body’s immune system to fight off the infection. Antibiotics are usually taken orally in the form of pills, capsules, or liquid solutions, or sometimes administered intravenously. They are not effective against viral infections, and using them inappropriately can lead to antibiotic resistance.
The "A:" is an explicit prompt format that's used in question answering. I used it here to tell the model that there is an expected further. In this example, it's not clear how this is useful vs not using it but we will leave it that for later examples. Let's just assume that this is too much information and want to summarize it further. We can instruct the model to summarize into one sentence like so:
Antibiotics are a type of medication used to treat bacterial infections. They work by either killing the bacteria or preventing them from reproducing, allowing the body’s immune system to fight off the infection. Antibiotics are usually taken orally in the form of pills, capsules, or liquid solutions, or sometimes administered intravenously. They are not effective against viral infections, and using them inappropriately can lead to antibiotic resistance.
Antibiotics are medications used to treat bacterial infections by either killing the bacteria or stopping them from reproducing, but they are not effective against viruses and overuse can lead to antibiotic resistance.
Without paying too much attention to the accuracy of the output above, which is something we will touch on in a later guide, the model tried to summarize the paragraph in one sentence. You can get clever with the instructions but we will leave that for a later chapter. Feel free to pause here and experiment to see if you get better results.
While language models are trained to perform natural language generation and related tasks, it's also very capable of performing classification and a range of other natural language processing (NLP) tasks.
Here is an example of a prompt that extracts information from a given paragraph.
Author-contribution statements and acknowledgements in research papers should state clearly and specifically whether, and to what extent, the authors used AI technologies such as ChatGPT in the preparation of their manuscript and analysis. They should also indicate which LLMs were used. This will alert editors and reviewers to scrutinize manuscripts more carefully for potential biases, inaccuracies and improper source crediting. Likewise, scientific journals should be transparent about their use of LLMs, for example when selecting submitted manuscripts.
Mention the large language model based product mentioned in the paragraph above:
By now it should be obvious that you can ask the model to perform different tasks by simply instructing it what to do. That's a powerful capability that AI product builders are already using to build powerful products and experiences.
One of the best ways to get the model to respond to specific answers is to improve the format of the prompt. As covered before, a prompt could combine instructions, context, input, and output indicators to get improved results. While these components are not required, it becomes a good practice as the more specific you are with instruction, the better results you will get. Below is an example of how this would look following a more structured prompt.
Context: Teplizumab traces its roots to a New Jersey drug company called Ortho Pharmaceutical. There, scientists generated an early version of the antibody, dubbed OKT3. Originally sourced from mice, the molecule was able to bind to the surface of T cells and limit their cell-killing potential. In 1986, it was approved to help prevent organ rejection after kidney transplants, making it the first therapeutic antibody allowed for human use.
So far, we have used simple instructions to perform a task. As a prompt engineer, you will need to get better at providing better instructions. But that's not all! You will also find that for harder use cases, just providing instructions won't be enough. This is where you need to think more about the context and the different elements you can use in a prompt. Other elements you can provide are `input data` or `examples`.
Let's try to demonstrate this by providing an example of text classification.
We gave the instruction to classify the text and the model responded with `'Neutral'` which is correct. Nothing is wrong with this but let's say that what we really need is for the model to give the label in the exact format we want. So instead of `Neutral` we want it to return `neutral`. How do we achieve this. There are different ways to do this. We care about specificity here, so the more information we can provide the prompt the better results. We can try providing examples to specify the correct behavior. Let's try again:
Perfect! This time the model returned `neutral` which is the specific label I was looking for. It seems that the example provided in the prompt helped the model to be specific in its output. To highlight why sometimes being specific is important, checkout this example and spot the problem:
Perhaps one of the more interesting things you can achieve with prompt engineering is instructing the LLM system on how to behave, its intent, and its identity. This is particularly useful when you are building conversational systems like customer service chatbots.
For instance, let's create a conversational system that's able to generate more technical and scientific responses to questions. Note how we are explicitly telling it how to behave through the instruction. This is sometimes referred to as *role prompting*.
Sure! Black holes are regions of spacetime where the gravitational force is so strong that nothing, not even light, can escape from it. They are created when a very massive star dies and its core collapses in on itself, forming a singularity of infinite density. The intense gravity of the singularity pulls in all the matter and radiation around it, creating the black hole.
```
Our AI research assistant sounds a bit too technical, right? Okay, let's change this behavior and instruct the system to give more accessible answers.
Sure! Black holes are created when a very massive star runs out of fuel and collapses in on itself. The gravity of the star is so strong that nothing, not even light, can escape its pull. This creates a point in space-time with an intense gravitational force called a black hole.
```
I think we made some progress. You can continue improving it. I am sure if you add more examples you might get even better results.
One application where LLMs are quite effective is code generation. Copilot is a great example of this. There are a vast number of code-generation tasks you can perform with clever prompts. Let's look at a few examples below.
Perhaps one of the most difficult tasks for an LLM today requires some form of reasoning. Reasoning is one of the areas that I am most excited about due to the types of complex applications that can emerge from LLMs.
There have been some improvements in tasks involving mathematical capabilities. That said, it's important to note that current LLMs struggle to perform reasoning tasks so this requires even more advanced prompt engineering techniques. We will cover these advanced techniques in the next guide. For now, we will cover a few basic examples to show arithmetic capabilities.
Much better, right? By the way, I tried this a couple of times and the system sometimes fails. If you provide better instruction combined with examples, it might help get more accurate results.
|Learn how to perform many different types of common tasks using the `openai` and `LangChain` library|[Getting Started with Prompt Engineering](../notebooks/pe-lecture.ipynb)|