UGRD-AI6100 AI: Prompt Engineering

1. Home
2. My courses
3. UGRD-AI6100-2323T
4. PRELIMINARY EXAMINATION
5. Prelim Exam

Started on Monday, 5 February 2024, 10:18 AM

State Finished
Completed on Monday, 5 February 2024, 10:41 AM
Time taken 22 mins 59 secs
Marks 47.00/50.00
Grade 94.00 out of 100.00
Question 1
Correct
Mark 1.00 out of 1.00

Flag question

Question text
Which type of prompt is used to generate text about a topic without any prior knowledge?

a.
Input/output prompts

b.
Few-shot prompts

c.
Adversarial prompts

d.
Zero-shot prompts

Question 2
Correct
Mark 1.00 out of 1.00
 Flag question

Question text
Which type of prompt can be used to generate creative or unexpected text, but may not be
as creative or unexpected as zero-shot prompts?

a.
Adversarial prompts

b.
Input/output prompts

c.
Zero-shot prompts

d.
Few-shot prompts

Question 3
Correct
Mark 1.00 out of 1.00

Flag question

Question text
What is the impact of adversarial prompts on the LLM?

a.
They confuse the LLM

b.
They limit the LLM's output

c.
They require the LLM to learn new information and generate text that is not similar to any of
the text it has seen before

d.
They have no impact on the LLM

Question 4
Correct
Mark 1.00 out of 1.00

Flag question

Question text
What is the quality of the response generated by a large language model dependent on?

a.
The quality of the prompt and the language model's dataset.

b.
The speed of the language model's processing.

c.
The size and complexity of the prompt.

d.
The training algorithm of the language model.

Question 5
Correct
Mark 1.00 out of 1.00

Flag question

Question text
What is the impact of experimenting with different ways to shorten the prompt without
sacrificing clarity or effectiveness?
a.
It makes the prompt more succinct

b.
It makes the prompt more specific

c.
It has no impact on the prompt

d.
It makes the prompt less clear and effective

Question 6
Correct
Mark 1.00 out of 1.00

Flag question

Question text
Where can adversarial prompts be used?

a.
Google AI's Pathways

b.
OpenAI's Jurassic-1 Jumbo

c.
OpenAI's Megatron-Turing NLG

d.
Google AI's LaMDA

Question 7
Correct
Mark 1.00 out of 1.00
 Flag question

Question text
What is a prompt in the context of large language models (LLMs)?

a.
A piece of text that guides the output of a large language model.

b.
A piece of code that generates text.

c.
A type of data structure.

d.
A type of programming language.

Question 8
Incorrect
Mark 0.00 out of 1.00

Flag question

Question text
Which of the following is an example of a succinct prompt for generating a poem about a
cat?

a.
"Write a poem about a feline."

b.
"Write a poem about an animal."

c.
"Write a poem about a cat that is lost."
d.
"Write a poem about a furry, four-legged creature that purrs and meows."

Question 9
Correct
Mark 1.00 out of 1.00

Flag question

Question text
What is the impact of succinct prompts on large language models (LLMs)?

a.
They help reduce noise in the dataset and focus on relevant information

b.
They have no impact on LLMs

c.
They make it harder for LLMs to focus on relevant information

d.
They lead to less accurate and creative text generation

Question 10
Correct
Mark 1.00 out of 1.00

Flag question

Question text
What is the primary tip for writing succinct prompts?

a.
Being as specific as possible
b.
Using unnecessary words or phrases

c.
Sacrificing clarity for effectiveness

d.
Avoiding specificity

Question 11
Correct
Mark 1.00 out of 1.00

Flag question

Question text
Which type of prompt tells the LLM to generate text that is different from a specific input?

a.
Adversarial prompts

b.
Few-shot prompts

c.
Input/output prompts

d.
Zero-shot prompts

Question 12
Correct
Mark 1.00 out of 1.00

Flag question

Question text
What is the primary function of a large language model when it receives a prompt?
a.
To find patterns that match the prompt in its dataset.

b.
To follow the prompt exactly as it is written.

c.
To create a response without considering the prompt.

d.
To ignore the prompt and generate random output.

Question 13
Correct
Mark 1.00 out of 1.00

Flag question

Question text
What is an example of a few-shot prompt for generating text in the style of Shakespeare?

a.
"Write a story about a robot who falls in love with a human."

b.
"Write a poem about a cat that explores the meaning of life."

c.
"Write a joke about a cat."

d.
"Write a poem about a cat in the style of Shakespeare."

Question 14
Correct
Mark 1.00 out of 1.00
 Flag question

Question text
Which type of prompt tells the LLM to generate text that matches a specific input?

a.
Input/output prompts

b.
Few-shot prompts

c.
Zero-shot prompts

d.
Adversarial prompts

Question 15
Correct
Mark 1.00 out of 1.00

Flag question

Question text
How does the length of the prompt depend on the complexity of the task?

a.
The length of the prompt has no impact on the complexity of the task

b.
Longer prompts are always better

c.
Short prompts are always better
d.
The length of the prompt depends on the complexity of the task

Question 16
Correct
Mark 1.00 out of 1.00

Flag question

Question text
What is the impact of using a less succinct prompt "Write a poem about a furry, four-legged
creature that purrs and meows" for a technical background?

a.
It makes the prompt more specific

b.
It makes the prompt easier for the LLM to understand

c.
It makes the prompt less specific and more open to interpretation

d.
It has no impact on the LLM

Question 17
Correct
Mark 1.00 out of 1.00

Flag question

Question text
What is the primary purpose of prompt engineering for text-based generative art?

a.
To make the art creation process more complex.
b.
To guide the output of large language models.

c.
To limit the creativity of language models.

d.
To eliminate the need for language models in art creation.

Question 18
Correct
Mark 1.00 out of 1.00

Flag question

Question text
What type of prompt would you use to generate text about a topic that the LLM has never
seen before?

a.
Zero-shot prompts

b.
Few-shot prompts

c.
Input/output prompts

d.
Adversarial prompts

Question 19
Correct
Mark 1.00 out of 1.00

Flag question

Question text
What should succinct prompts avoid in terms of language specificity?

a.
Using technical terms

b.
Using vague or general language

c.
Being as specific as possible

d.
Being relevant to the task at hand

Question 20
Correct
Mark 1.00 out of 1.00

Flag question

Question text
What is a key characteristic of effective prompts?

a.
Vague and general.

b.
Lengthy and ambiguous.

c.
Clear, concise, and specific.

d.
Abstract and theoretical.

Question 21
Correct
Mark 1.00 out of 1.00
 Flag question

Question text
What is prompt engineering?

a.
The process of crafting instructions that guide the output of a large language model.

b.
The process of creating technical prompts for software development.

c.
The process of generating random instructions for language models.

d.
The process of designing physical prompts for creative content.

Question 22
Correct
Mark 1.00 out of 1.00

Flag question

Question text
What is the primary benefit of prompt engineering?

a.
Generating random outputs from language models.

b.
Controlling the output of large language models.

c.
Creating complex and ambiguous prompts.
d.
Limiting the capabilities of language models.

Question 23
Correct
Mark 1.00 out of 1.00

Flag question

Question text
What is the impact of using a succinct prompt for generating a poem about a cat?

a.
It makes the task more confusing

b.
It has no impact on the task

c.
It makes the task less clear and easy to understand

d.
It makes the task clear and easy to understand

Question 24
Correct
Mark 1.00 out of 1.00

Flag question

Question text
Why is it important for a prompt to be clear and easy to understand?

a.
To use language that the LLM can understand

b.
To avoid using language that the LLM can understand

c.
To use jargon and technical terms

d.
To make the LLM's job more difficult

Question 25
Correct
Mark 1.00 out of 1.00

Flag question

Question text
What is the best way to learn how to write effective prompts?

a.
By not using prompts at all

b.
By using the same type of prompt for every task

c.
By experimenting with different types of prompts

d.
By avoiding experimentation

Question 26
Correct
Mark 1.00 out of 1.00

Flag question

Question text
What is the importance of well-structured prompts in guiding the output of the LLM?
a.
Well-structured prompts limit the LLM's output

b.
Well-structured prompts confuse the LLM

c.
Well-structured prompts are not important

d.
Well-structured prompts are important for the LLM to understand

Question 27
Correct
Mark 1.00 out of 1.00

Flag question

Question text
What is the purpose of a prompt in guiding the output of a large language model (LLM)?

a.
To ignore the output of the LLM

b.
To guide the output of the LLM

c.
To limit the output of the LLM

d.
To confuse the LLM

Question 28
Correct
Mark 1.00 out of 1.00
 Flag question

Question text
What is the significance of experimenting with different techniques for prompt engineering?

a.
It only confuses the language model.

b.
It slows down the prompt engineering process.

c.
It can improve the effectiveness of prompts.

d.
It has no impact on the effectiveness of prompts.

Question 29
Correct
Mark 1.00 out of 1.00

Flag question

Question text
What type of patterns does a large language model use to generate a response?

a.
Random patterns from its dataset.

b.
Only patterns related to sentence structures.

c.
Patterns related to the meaning of individual words and the structure of sentences.
d.
Only patterns related to individual words.

Question 30
Correct
Mark 1.00 out of 1.00

Flag question

Question text
Which type of prompt is the most efficient and a good choice for platforms with limited
resources?

a.
Input/output prompts

b.
Adversarial prompts

c.
Zero-shot prompts

d.
Few-shot prompts

Question 31
Correct
Mark 1.00 out of 1.00

Flag question

Question text
What is the impact of tailoring the prompt to the specific task at hand?

a.
It makes the prompt more verbose
b.
It makes the prompt less relevant

c.
It has no impact on the prompt

d.
It makes the prompt more succinct

Question 32
Correct
Mark 1.00 out of 1.00

Flag question

Question text
What is the primary purpose of using keywords and phrases relevant to the task in a
prompt?

a.
To limit the language model's capabilities.

b.
To distract the language model from the task.

c.
To help the language model focus on the most important information.

d.
To confuse the language model.

Question 33
Correct
Mark 1.00 out of 1.00

Flag question

Question text
What is the impact of using succinct prompts on the clarity of the task?

a.
It makes the task less clear and easy to understand

b.
It makes the task more confusing

c.
It makes the task clear and easy to understand

d.
It has no impact on the clarity of the task

Question 34
Correct
Mark 1.00 out of 1.00

Flag question

Question text
What is the impact of using unnecessary words or phrases in a prompt?

a.
It makes the prompt less clear and effective

b.
It has no impact on the prompt

c.
It makes the prompt more specific

d.
It makes the prompt more succinct

Question 35
Incorrect
Mark 0.00 out of 1.00
 Flag question

Question text
What is an example of an input/output prompt for generating text?

a.
"Write a poem about a cat that explores the meaning of life."

b.
"Write a story about a robot who falls in love with a human."

c.
"Write a joke about a cat."

d.
"Write a poem about something beautiful."

Question 36
Incorrect
Mark 0.00 out of 1.00

Flag question

Question text
What is an example of an adversarial prompt for generating text that is thought-provoking?

a.
"Write a poem about a cat that is not like any other poem you have written."

b.
"Write a poem about a cat that explores the meaning of life."

c.
"Write a joke about a cat."
d.
"Write a story about a robot who falls in love with a human."

Question 37
Correct
Mark 1.00 out of 1.00

Flag question

Question text
What is the impact of using a succinct prompt "Write a poem about a cat" for a non-
technical background?

a.
It makes it harder for the LLM to understand

b.
It has no impact on the LLM

c.
It makes the prompt easier for the LLM to understand

d.
It makes the prompt less specific

Question 38
Correct
Mark 1.00 out of 1.00

Flag question

Question text
Which platforms are better suited for zero-shot prompts?

a.
Platforms with a large dataset of text
b.
Platforms with a limited dataset of text

c.
Platforms with a smaller dataset of text

d.
Platforms with no dataset of text

Question 39
Correct
Mark 1.00 out of 1.00

Flag question

Question text
What is the first step in processing a prompt by a large language model?

a.
Finding patterns that match the prompt.

b.
Understanding the meaning of the prompt.

c.
Generating a response.

d.
Breaking the prompt down into individual words and phrases.

Question 40
Correct
Mark 1.00 out of 1.00

Flag question

Question text
What is the difference between natural language prompts and technical prompts?
a.
Technical prompts are easier to write

b.
Natural language prompts are less precise

c.
Technical prompts are less precise

d.
Natural language prompts are more precise

Question 41
Correct
Mark 1.00 out of 1.00

Flag question

Question text
Which type of prompt is used to generate text about a topic based on a few examples?

a.
Zero-shot prompts

b.
Adversarial prompts

c.
Few-shot prompts

d.
Input/output prompts

Question 42
Correct
Mark 1.00 out of 1.00
 Flag question

Question text
What is the recommended approach for writing effective prompts?

a.
Use complex technical terms to challenge the language model.

b.
Use keywords and phrases relevant to the task.

c.
Use ambiguous and vague language.

d.
Avoid being specific about the task.

Question 43
Correct
Mark 1.00 out of 1.00

Flag question

Question text
What is the importance of succinctness in prompt writing?

a.
It makes the prompt longer and more complex

b.
It confuses the language model

c.
It makes the prompt more verbose
d.
It reduces the noise in the dataset

Question 44
Correct
Mark 1.00 out of 1.00

Flag question

Question text
What is the expected outcome after completing Module 001 of the course?

a.
Proficiency in writing computer code for language models.

b.
Expertise in natural language processing algorithms.

c.
Understanding the basic concepts of prompt engineering.

d.
Ability to build a large language model from scratch.

Question 45
Correct
Mark 1.00 out of 1.00

Flag question

Question text
What is an example of a zero-shot prompt for generating a story?

a.
"Write a poem about a cat that is not like any other poem you have written."

b.
"Write a poem about a cat."

c.
"Write a story about a robot who falls in love with a human."

d.
"Write a script for a movie about a cat who solves a mystery."

Question 46
Correct
Mark 1.00 out of 1.00

Flag question

Question text
How can using a variety of prompts help in generating more creative and interesting text?

a.
Using a variety of prompts limits the creativity of the text

b.
Using a variety of prompts can help generate more creative and interesting text

c.
Using a variety of prompts has no impact on the creativity of the text

d.
Using a variety of prompts confuses the LLM

Question 47
Correct
Mark 1.00 out of 1.00

Flag question

Question text
What is the impact of specificity on the likelihood of generating the desired output from a
prompt?
a.
Specific prompts have no impact on the likelihood of generating the desired output

b.
Specific prompts increase the likelihood of generating the desired output

c.
Specific prompts confuse the LLM

d.
Specific prompts decrease the likelihood of generating the desired output

Question 48
Correct
Mark 1.00 out of 1.00

Flag question

Question text
What is the most important step in processing a prompt by a large language model?

a.
Breaking the prompt down into individual words and phrases.

b.
Generating a response.

c.
Understanding the meaning of the prompt.

d.
Finding patterns that match the prompt.

Question 49
Correct
Mark 1.00 out of 1.00
 Flag question

Question text
Which type of prompt is a good choice for platforms used for creative writing or generating
ideas?

a.
Input/output prompts

b.
Adversarial prompts

c.
Few-shot prompts

d.
Zero-shot prompts

Question 50
Correct
Mark 1.00 out of 1.00

Flag question

Question text
What is the purpose of prompts for those with a non-technical background?

a.
To confuse the LLM

b.
To tell the LLM what to do

c.
To limit the LLM's output
d.
To ignore the LLM's output