Context by Cohere
Large Language Models and Where to Use Them

Large Language Models and Where to Use Them: Part 1

Over the past few years, large language models (LLMs) have evolved from emerging to mainstream technology. In this blog post, we'll explore some of the most common natural language processing (NLP) use cases that they can address. This is part one of a two-part series.

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. But 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:

  1. Generate
  2. Summarize
  3. Rewrite
  4. Extract
  5. Search/Similarity
  6. Cluster
  7. 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. The goal here is to have the model generate the first paragraph of a blog post. First, we prepare a short line of context about what we’d like the model to write. Then, we prepare two examples — each containing the blog’s title, its audience, the tone of voice, and the matching paragraph.

Finally, we feed the model with this prompt, together with the information for the new blog. And the model will duly generate the text that matches the context, as seen below.

This program will generate an introductory paragraph to a blog post given a blog title, audience, and tone of voice.
Blog Title: Best Activities in Toronto
Audience: Millennials
Tone of Voice: Lighthearted
First Paragraph: Looking for fun things to do in Toronto? When it comes to exploring Canada's largest city, there's an ever-evolving set of activities to choose from. Whether you're looking to visit a local museum or sample the city's varied cuisine, there is plenty to fill any itinerary. In this blog post, I'll share some of my favorite recommendations
Blog Title: Mastering Dynamic Programming
Audience: Developers
Tone: Informative
First Paragraph: In this piece, we'll help you understand the fundamentals of dynamic programming, and when to apply this optimization technique. We'll break down bottom-up and top-down approaches to solve dynamic programming problems.
Blog Title: How to Get Started with Rock Climbing
Audience: Athletes
Tone: Enthusiastic
First Paragraph:


Interested in trying rock climbing? Whether you're a beginner or a seasoned climber, you'll find a wealth of options for the perfect rock climbing excursion. In this piece, I'll share some of the best rock climbing spots in the United States to help you plan your next adventure.

You can test it out by accessing the saved preset.

In fact, the excerpt you read at the beginning of this blog was generated using this preset!

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.


Passage: Is Wordle getting tougher to solve? Players seem to be convinced that the game has gotten harder in recent weeks ever since The New York Times bought it from developer Josh Wardle in late January. The Times has come forward and shared that this likely isn't the case. That said, the NYT did mess with the back end code a bit, removing some offensive and sexual language, as well as some obscure words There is a viral thread claiming that a confirmation bias was at play. One Twitter user went so far as to claim the game has gone to "the dusty section of the dictionary" to find its latest words.

TLDR: Wordle has not gotten more difficult to solve.
Passage: ArtificialIvan, a seven-year-old, London-based payment and expense management software company, has raised $190 million in Series C funding led by ARG Global, with participation from D9 Capital Group and Boulder Capital. Earlier backers also joined the round, including Hilton Group, Roxanne Capital, Paved Roads Ventures, Brook Partners, and Plato Capital.

TLDR: ArtificialIvan has raised $190 million in Series C funding.
Passage: The National Weather Service announced Tuesday that a freeze warning is in effect for the Bay Area, with freezing temperatures expected in these areas overnight. Temperatures could fall into the mid-20s to low 30s in some areas. In anticipation of the hard freeze, the weather service warns people to take action now.



A hard freeze is expected to hit the Bay Area tonight.

You can test it out by accessing the saved preset.

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.


This is voice-to-text transcription corrector. Given a transcribed excerpt with errors, the model responds with the correct version of the excerpt.

Incorrect transcription: I am balling into hay to read port missing credit card. I lost by card when I what's at the grocery store and I need to see sent a new one.

Correct transcription: I am calling in today to report a missing credit card. I lost my card when I was at the grocery store and I need to be sent a new one.
Incorrect transcription: Can you repeat the dates for the three and five dear fixed mortgages? I want to compare them a gain the dates I was quoted by a other broker.

Correct transcription: Can you repeat the rates for the three and five year fixed mortgages? I want to compare them against the rates I was quoted by another broker.
Incorrect transcription: I got got charged interest on ly credit card but I paid my pull balance one day due date. I not missed a pavement year yet. Man you reverse the interest charge?

Correct transcription:


I got charged interest on my credit card last month but I paid my balance in full on the due date. I haven't missed a payment yet. Man, you reverse the interest charge?

You can test it out by accessing the saved preset.

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.


This program will extract relevant information from contracts. Here are some examples:

Contract: This influencer Marketing Agreement ("Agreement") dated on the 23 day of August, 2022 (the "Effective Date") is made between Oren & Co (the "Influencer") and Brand Capital (the "Company") regarding. The Company will compensate the Influencer with five thousand dollars ($5000.00) for the overall Services rendered. This Agreement is effective upon its signing until July 31, 2023, when the final LinkedIn post is uploaded and all Services and compensation are exchanged.

Extracted Text:
Influencer: Oren & Co
Company: Brand Capital
Contract: This Music Recording Agreement ("Agreement") is made effective as of the 13 day of December, 2021 by and between Good Kid, a Toronto-based musical group ("Artist") and Universal Music Group, a record label with license number 545345 ("Recording Label"). Artist and Recording Label may each be referred to in this Agreement individually as a "Party" and collectively as the "Parties." Work under this Agreement shall begin on March 15, 2022.

Extracted Text:


Artist: Good Kid
Recording Label: Universal Music Group

You can test it out by accessing the saved preset.

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


In part two of this series, we’ll continue our exploration of the remaining three use case categories (Search/Similarity, Cluster, and Classify). We’ll also explore how LLM APIs can help address more complex use cases. The world is complex, and a lot of problems can only be tackled by piecing multiple NLP models together. We’ll look at some examples of how we can quickly snap together a combination of API endpoints in order to build more complete solutions.

Get access to the Cohere platform here.

Keep reading