You can find Part 2 here.

A large language model (LLM) is a type of machine learning model that can handle a wide range of natural language processing (NLP) use cases. However, due to their versatility, LLMs can be a bit overwhelming for newcomers who are trying to understand when and where to use these models.

In this blog series, we’ll simplify LLMs by mapping out the seven broad categories of use cases where you can apply them, with examples from Cohere's LLM platform. Hopefully, this can serve as a starting point as you begin working with the Cohere API, or even seed some ideas for the next thing you want to build.

The seven use case categories are:

Generate
Summarize
Rewrite
Extract
Search/Similarity
Cluster
Classify

Because of the general-purpose nature of LLMs, the range of use cases and relevant industries within each category is extremely wide. This post will not attempt to delve too deeply into each, but it will provide you with enough ideas and examples to help you start experimenting.

1. Generate

Probably the first thing that comes to mind when talking about LLMs is their ability to generate original and coherent text. And that’s what this use case category is all about. LLMs are pre-trained using a huge collection of text gathered from a variety of sources. This means that they are able to capture the patterns of how language is used and how humans write.

Getting the best out of these generation models is now becoming a whole field of study in and of itself called prompt engineering. In fact, the first four use case categories on our list all leverage prompt generation in their own ways.

More on the other three later, but the basic idea in prompt engineering is to provide a context for a model to work with. Prompt engineering is a vast topic, but at a very high level, the idea is to provide a model with a small amount of contextual information as a cue for generating a specific sequence of text.

One way to set up the context is to write a few lines of a passage for the model to continue. Imagine writing an essay or marketing copy where you would begin with the first few sentences about a topic, and then have the model complete the paragraph or even the whole piece.

Another way is by writing a few example patterns that indicate the type of text that we want the model to generate. This is an interesting one because of the different ways we can shape the models and the various applications that it entails.

Let’s take one example with product description generation. Here we create a prompt that asks for a launch e-mail for a wireless headphones product.

Prompt:

The CO-1T is a wireless headphone product that uses Bluetooth technology to connect to your devices. \
It has a long battery life and can be quickly charged using the included USB cable. The headphone is \
lightweight and comfortable, ideal for long periods of use. It has a built-in microphone for making calls, \
and a button to control the volume. The CO-1T is a great choice for anyone looking for a wireless headphone \
product with great battery life.

Create an email about the product above mentioning the following:
- announce product launch
- create a call to action
- mention live chat for support

Completion:


We are thrilled to announce the launch of our newest wireless headphones, the CO-1T! These headphones are designed to offer a seamless and convenient listening experience with the use of Bluetooth technology, giving you the freedom to connect to your devices wirelessly.

The CO-1T is crafted to be comfortable and lightweight, making it the perfect companion for your daily commutes or workouts. With a long-lasting battery life, you'll never have to worry about running out of charge during your day. Plus, a quick charge feature ensures you're always ready to go. Simply use the included USB cable for efficient charging.

Control your volume and manage your calls effortlessly with the built-in microphone and easy-to-use button controls. Experience the convenience of wireless connectivity and immerse yourself in crystal-clear audio.

We believe our product will provide an exceptional listening experience and enhance your daily routine. Try it out today and discover the convenience of wireless freedom!

If you have any questions or need further assistance, our team is here to help. Feel free to reach out to us through our live chat feature on our website, and we'll be happy to assist you.

Thank you, and we hope you enjoy the CO-1T wireless headphones!

That was just one example, but how we prompt a model is limited only by our creativity. Here are some other examples:

Writing product descriptions, given the product name and keywords
Writing chatbot/conversational AI responses
Developing a question-answering interface
Writing emails, given the purpose/command
Writing headlines and paragraphs

2. Summarize

The second use case category, which also leverages prompt engineering, is text summarization. Think about the amount of text that we deal with on a typical day, such as reports, articles, meeting notes, emails, transcripts, and so on. We can have an LLM summarize a piece of text by prompting it with a few examples of a full document and its summary.

The following is an example of article summarization, where we prepare the prompt to contain the full passage of an article and its one-line summary.

Prompt:

Summarize the following.

Customer reviews of the CO-1T wireless headphones:

"The CO-1T is a great pair of headphones! The design is sleek and modern, and the headphones are \
very comfortable to wear. The sound quality is excellent, and I can hear every detail of my music. \
The built-in microphone means I can make calls without having to take my phone out of my pocket. I \
highly recommend the CO-1T to anyone looking for a great pair of wireless headphones!"

"I'm very disappointed with the CO-1T. The design is nice, but the battery life is terrible. I can \
only use them for a few hours before they need to be recharged. This is very inconvenient, and I'm \
not sure if I can recommend them to anyone."

"The CO-1T is a mixed bag. The speaker quality is great, but the built-in microphone's quality is \
poor. I can hear every detail of my music, but my voice sounds distorted when I make calls. The \
design is nice, and the headphones are comfortable to wear, but the battery life is only average. \
I'm not sure if I can recommend them to anyone."

Completion:

The CO-1T wireless headphones have a sleek, modern design and are comfortable to wear. They offer excellent sound quality, with clear and detailed audio. However, the reviews are mixed when it comes to the built-in microphone's quality, with some users reporting distortion. The battery life is a major downside, lasting only a few hours on a single charge. Overall, the CO-1T seems like a decent option for those prioritizing sound quality and comfort, but the mediocre battery life and inconsistent microphone quality might be dealbreakers for some.

Here are some other example documents where LLM summarization will be useful:

Customer support chats
Environmental, Social, and Governance (ESG) reports
Earnings calls
Paper abstracts
Dialogues and transcripts

3. Rewrite

Another flavor of prompt engineering is text rewriting. This is another of those tasks that we do every day and spend a lot of time on, and if we could automate them, it would free us up to work on more creative tasks.

Rewriting text can mean different things and take different forms, but one common example is text correction. The following is the task of correcting the spelling and grammar in voice-to-text transcriptions. We prepare the prompt with a short bit of context about the task, followed by examples of incorrect and corrected transcriptions.

Prompt:


Create a version of this product description that's tailored towards college students.

The CO-1T is a wireless headphone product that uses Bluetooth technology to connect to your devices. \
It has a long battery life and can be quickly charged using the included USB cable. The headphone is \
lightweight and comfortable, ideal for long periods of use. It has a built-in microphone for making calls, \
and a button to control the volume. The CO-1T is a great choice for anyone looking for a wireless headphone \
product with great battery life.

Completion:

The CO-1T headphones are the ultimate wireless companion for any college student. With Bluetooth capabilities, you can easily connect to your laptop, phone, or tablet without the hassle of tangling cords. Study for long hours without discomfort or interruption - the lightweight design ensures comfort and the long battery life keeps you connected throughout the day. Quick charge the batteries using the included USB cable when you're running short on time, and use the built-in microphone to stay connected with your friends and family. Control your audio easily with the volume button, and focus on what really matters - acing your courses!

Here are some other example use cases for using an LLM to rewrite text:

Paraphrase a piece of text in a different voice
Build a spell checker that corrects text capitalizations
Rephrase chatbot responses
Redact personally identifiable information
Turn a complex piece of text into a digestible form

4. Extract

Text extraction is another use case category that can leverage a generation LLM. The idea is to take a long piece of text and extract only the key information or words from the text.

The following is the task of extracting relevant information from contracts. We prepare the prompt with a short bit of context about the task, followed by a couple of example contracts and the extracted text.

Prompt:

Extract the product, refund reason and pick-up address from this email:

I am writing to request a refund for a recent CO-1T purchase I made on your platform. \
Unfortunately, the produce has not met my expectations due to its poor battery life. \
Please arrange for the pick-up at this address: to 171 John Street, Toronto ON, M5T 1X2.

Completion:

Product: CO-1T
Refund Reason: Poor battery life
Pick-up Address: 171 John Street, Toronto ON, M5T 1X2

Some other use cases in this category include:

Extract named entities from a document
Extract keywords and keyphrases from articles
Flag for personally identifiable information
Extract supplier and contract terms
Create tags for blogs

Conclusion

In part two, we’ll explore the remaining three use case categories (Search, Cluster, and Classify).

Get access to the Cohere platform here.

Large Language Models and Where to Use Them: Part 1