Skip to content
Oak National Academy
Oak National Academy
View my library
0
Teachers
Pupils
View unit
New
New
Lesson 3 of 8
  • Year 10

Chatbot applications and other LLMs

I can describe the purpose of LLMs and explain why the output may not be trustworthy.

Download all resources
Share activities with pupils
View unit
Lesson 3 of 8
New
New
  • Year 10

Chatbot applications and other LLMs

I can describe the purpose of LLMs and explain why the output may not be trustworthy.

Download all resources
Share activities with pupils

These resources will be removed by end of Summer Term 2025.

Switch to our new teaching resources now - designed by teachers and leading subject experts, and tested in classrooms.

These resources were created for remote use during the pandemic and are not designed for classroom teaching.

View new resources

Lesson details

Key learning points

  1. LLMs are trained on large amounts of text data.
  2. The aim of LLMs and chatbot applications is to provide realistic conversations by predicting the next word or phrase.
  3. There is no guarantee that data used to train LLMs is accurate, unbiased and trustworthy.
  4. Bias is when the output of an AI model favours some things and deprioritises or excludes others.

Keywords

  • Language model - an AI system used to produce or complete written text based on patterns identified in training data

  • Prediction - an estimate of what might happen next based on patterns found in training data

  • Bias - when something is unfair towards or against something or someone

  • Trust - confidence that something will work as expected and produce reliable and fair results

Common misconception

Large Language Models (LLMs) understand what they’re saying, like a human does.

LLMs do not understand language or meaning. They generate responses by predicting the most likely next word based on patterns in the data they were trained on, not because they understand the content like a human does.


To help you plan your year 10 computing lesson on: Chatbot applications and other LLMs, download all teaching resources for free and adapt to suit your pupils' needs...

Use real-world examples of LLM responses from AI writing tools and ask students to spot possible bias or unfairness. This encourages critical thinking and helps students see that LLMs don’t “understand” content — they generate text based on patterns in data, which may include biased information.
Teacher tip

Equipment

Licence

This content is © Oak National Academy Limited (2025), licensed on Open Government Licence version 3.0 except where otherwise stated. See Oak's terms & conditions (Collection 2).

Lesson video

Skip lesson video

Loading...

Prior knowledge starter quiz

Download quiz pdf

6 Questions

Q1.
What is the main purpose of a predictive AI system?

to create new music
to draw pictures
Correct answer: to predict what might happen next
to store information

Q2.
Which task would a generative AI system be best at?

forecasting the weather
calculating sums
sorting emails
Correct answer: writing a new poem

Q3.
What is the term for the information given to an AI system so it can learn?

Correct Answer: training data

Q4.
Put these actions in order for using predictive AI to forecast exam results:

1 - collect past exam scores
2 - train the AI system
3 - input new student data
4 - predict future results

Q5.
Which keyword describes an AI system that can make new things like pictures or music?

Correct Answer: generative, generative AI

Q6.
Match each example to the correct keyword:

Correct Answer:generative,making a new painting using AI

making a new painting using AI

Correct Answer:predictive,guessing next week’s weather

guessing next week’s weather

Correct Answer:training data,providing a set of sample essays for AI to study

providing a set of sample essays for AI to study

Assessment exit quiz

Download quiz pdf

6 Questions

Q1.
Put these steps in order for how an LLM creates a response:

1 - receives a user’s question
2 - analyses the question using patterns from training data
3 - predicts the next word or phrase
4 - produces a complete response

Q2.
What is a Large Language Model (LLM) mainly trained on?

pictures and videos
mathematical equations only
spoken conversations only
Correct answer: large collections of text data

Q3.
What is the term for when the output of an AI model unfairly favours or excludes certain groups or ideas?

Correct Answer: bias

Q4.
What is the main aim of a chatbot using an LLM?

Correct answer: to provide realistic conversations by predicting words
to create computer games
to translate languages
to solve maths problems

Q5.
Match each example to the correct keyword:

Correct Answer:bias,the model always prefers one type of answer

the model always prefers one type of answer

Correct Answer:prediction,the AI creates the next word in a sentence

the AI creates the next word in a sentence

Correct Answer:trust,confidence that the model’s output is fair

confidence that the model’s output is fair

Correct Answer:language model,completing a story based on previous sentences

completing a story based on previous sentences

Q6.
Which statement about the data used to train LLMs is true?

It is always accurate and fair.
Correct answer: It may contain errors and bias.
It only comes from trusted sources.
It never changes.