Unit 5: Generative AI & Ethics; Prompt Engineering - Practice Quiz

INT428 — Artificial Intelligence Essentials 60 Questions
0 Correct 0 Wrong 60 Left
0/60

1 What is the primary goal of a generative AI model?

Fundamentals of Generative AI Easy
A. To classify data into fixed categories
B. To create new content such as text, images, or audio
C. To delete redundant data from storage
D. To encrypt data for secure transfer

2 What does the abbreviation LLM stand for?

LLMs Easy
A. Logical Learning Machine
B. Linear Language Method
C. Large Language Model
D. Layered Learning Module

3 A GAN consists of which two competing networks?

GANs Easy
A. Sender and Receiver
B. Trainer and Tester
C. Generator and Discriminator
D. Encoder and Decoder

4 How do diffusion models typically generate images?

Diffusion Easy
A. By gradually removing noise from a random signal
B. By copying pixels from existing images
C. By compressing images into smaller files
D. By translating text into binary code

5 Generative models learn to produce new data by understanding what from the training data?

How generative models work Easy
A. The storage location
B. The exact file sizes
C. The color of the labels
D. The underlying patterns and distribution

6 Which of the following is a common industrial application of generative AI?

Industrial applications (content creation, automation) Easy
A. Measuring room temperature
B. Automated content creation for marketing
C. Cleaning office floors
D. Physically manufacturing steel beams

7 Which of these is a major ethical concern with generative AI?

Ethics and Responsible Use of Generative AI Easy
A. Creation of deepfakes and misinformation
B. Lower electricity bills
C. Faster internet download speeds
D. Improved keyboard design

8 In the context of AI, what is a prompt?

Fundamentals of prompt Easy
A. The hardware running the model
B. The final output image
C. The training dataset size
D. The input or instruction given to a model

9 Why is prompt engineering important?

Importance of Prompt Engineering Easy
A. It replaces the need for electricity
B. It reduces the physical size of the computer
C. It helps obtain more accurate and relevant model outputs
D. It increases the monitor resolution

10 What is the main task of a language model?

Overview of language models Easy
A. Sorting numbers in ascending order
B. Rendering 3D graphics
C. Predicting the next word or token in a sequence
D. Managing network firewalls

11 Which element makes a prompt more effective?

Key elements of a good prompt Easy
A. Leaving it completely empty
B. Being as vague as possible
C. Being clear and specific
D. Using random symbols only

12 What is a prompt pattern?

Prompt Patterns Easy
A. A hardware wiring diagram
B. A reusable structure for writing effective prompts
C. A method for cooling servers
D. A type of computer virus

13 What does prompt tuning primarily aim to improve?

Prompt Tuning Easy
A. The length of network cables
B. The performance of a model on specific tasks
C. The physical weight of the server
D. The color scheme of the interface

14 Which of the following is an example of a generative AI output?

Fundamentals of Generative AI Easy
A. A deleted file log
B. An AI-written poem
C. A sorted spreadsheet
D. A network ping result

15 Which of the following is an example of a popular LLM-based application?

LLMs Easy
A. A file compression tool
B. A chatbot that answers questions in natural language
C. A calculator app
D. A spreadsheet that adds numbers

16 In a GAN, what is the role of the discriminator?

GANs Easy
A. To distinguish real data from generated data
B. To store the training dataset
C. To label the output categories
D. To generate new fake data

17 Which practice supports responsible use of generative AI?

Ethics and Responsible Use of Generative AI Easy
A. Ignoring copyright rules
B. Disclosing when content is AI-generated
C. Spreading unverified information
D. Hiding all sources of data

18 Generative AI helps automation in industry by:

Industrial applications (content creation, automation) Easy
A. Turning off all computers
B. Slowing down production lines
C. Manually typing every report by hand
D. Generating repetitive documents and reports automatically

19 Providing context in a prompt helps the model to:

Key elements of a good prompt Easy
A. Understand the situation and give relevant answers
B. Change its programming language
C. Run faster on old hardware
D. Reduce its memory usage

20 Which type of content are diffusion models most commonly used to generate?

Diffusion Easy
A. Database indexes
B. Network packets
C. Spreadsheet formulas
D. Images

21 A team wants a model that can produce brand-new product images that never existed in the training set, rather than labeling existing images. Which category of model best fits this requirement?

Fundamentals of Generative AI Medium
A. A discriminative model
B. A rule-based classifier
C. A generative model
D. A regression model

22 Why can a large language model produce a grammatically coherent answer to a question it was never explicitly trained to answer?

LLMs Medium
A. It predicts the next token based on learned statistical patterns of language
B. It compiles the prompt into executable code
C. It stores every possible answer in a lookup table
D. It queries the internet in real time for each token

23 In a GAN, the generator's training signal comes primarily from which source?

GANs Medium
A. The reconstruction error against the input
B. The gradient of a diffusion noise schedule
C. The discriminator's feedback on whether samples look real
D. A fixed labeled dataset of correct outputs

24 During GAN training a generator begins producing only a few near-identical outputs regardless of input noise. What problem is this?

GANs Medium
A. Overfitting the discriminator
B. Gradient explosion
C. Vanishing gradients
D. Mode collapse

25 What is the core idea behind how a diffusion model generates an image?

Diffusion Medium
A. It adds noise to a class label until an image appears
B. It searches a database for the closest matching image
C. It concatenates two real images and blends them
D. It learns to gradually denoise random noise into a coherent sample

26 A diffusion model has a forward process and a reverse process. What does the forward process do?

Diffusion Medium
A. Progressively adds noise to real data over many steps
B. Removes noise to reconstruct the image
C. Classifies the image into categories
D. Optimizes the discriminator weights

27 Why is sampling (rather than always choosing the single most likely token) often used when generating text?

How generative models work Medium
A. It removes the need for a training dataset
B. It guarantees factually correct outputs
C. It reduces the model size at inference
D. It introduces controlled variety and avoids repetitive text

28 Raising the temperature parameter during text generation generally has what effect?

How generative models work Medium
A. Makes output more random and creative
B. Increases the model's context window
C. Reduces the vocabulary size
D. Makes output more deterministic and focused

29 A marketing team uses generative AI to draft first versions of email campaigns that humans then edit. This is best described as which use pattern?

Industrial applications (content creation, automation) Medium
A. Human-in-the-loop content assistance
B. Fully autonomous decision-making
C. Real-time fraud detection
D. Data anonymization

30 Which scenario is the most appropriate use of generative AI for business automation?

Industrial applications (content creation, automation) Medium
A. Summarizing lengthy support tickets into action items
B. Serving as the sole legal authority for contracts
C. Guaranteeing 100% factual medical diagnoses
D. Replacing all human oversight in finance

31 A generative model trained on historical hiring data recommends fewer women for technical roles. What is the underlying ethical issue?

Ethics and Responsible Use of Generative AI Medium
A. Low sampling temperature
B. Bias inherited from training data
C. Model overfitting
D. Insufficient context window

32 When an LLM confidently states false information as if it were true, this behavior is commonly called:

Ethics and Responsible Use of Generative AI Medium
A. Regularization
B. Tokenization
C. Hallucination
D. Quantization

33 Which practice best supports responsible use when deploying a generative AI chatbot to the public?

Ethics and Responsible Use of Generative AI Medium
A. Removing all content filters for speed
B. Hiding the AI's identity to seem more human
C. Training only on a single author's writing
D. Disclosing that users are interacting with an AI system

34 In prompting an LLM, what does the term "context" most accurately refer to?

Fundamentals of prompt Medium
A. The GPU memory used during inference
B. The number of layers in the network
C. The model's internal weight matrix
D. The background information and instructions supplied to guide the response

35 Two users ask an LLM the same underlying question but get very different quality answers. What most likely explains this?

Importance of Prompt Engineering Medium
A. The model was retrained between the two queries
B. Differences in how each prompt was phrased and structured
C. One user had a faster internet connection
D. The model uses a different language for each user

36 Compared with older n-gram language models, transformer-based models are better at capturing long-range dependencies primarily because of:

Overview of language models Medium
A. Their smaller vocabulary size
B. Their reliance on fixed word frequencies
C. Their use of the self-attention mechanism
D. Their lack of any training data

37 Which revision most improves the prompt "Write about dogs" for a specific, useful result?

Key elements of a good prompt Medium
A. "Write a 100-word beginner guide on training a puppy to sit"
B. "Tell me dog stuff"
C. "Write about dogs quickly"
D. "Dogs, please"

38 You want an LLM to return output that a program can parse automatically. Which prompt element is most important to include?

Key elements of a good prompt Medium
A. A request to be as verbose as possible
B. A clear specification of the desired output format
C. An apology for the difficulty
D. A random seed value

39 Providing an LLM with a few input-output examples before the real task, so it infers the pattern, is known as which prompting technique?

Prompt Patterns Medium
A. Zero-shot prompting
B. Fine-tuning
C. Gradient descent
D. Few-shot prompting

40 How does prompt tuning differ from full fine-tuning of a language model?

Prompt Tuning Medium
A. It retrains every weight in the model from scratch
B. It changes the model architecture entirely
C. It learns a small set of soft prompt parameters while keeping model weights frozen
D. It only edits the tokenizer vocabulary

41 In a standard GAN, the generator's loss can suffer from vanishing gradients early in training when the discriminator is too strong. Which reformulation of the generator objective was proposed to mitigate this specific issue?

GANs Hard
A. Maximizing the discriminator's entropy over real samples
B. Minimizing the distance between real and fake images
C. Minimizing as originally specified
D. Maximizing (the non-saturating loss)

42 In a Denoising Diffusion Probabilistic Model (DDPM), the forward process adds noise over steps. What does the model actually learn to predict during training in the common parameterization?

Diffusion Hard
A. The exact reverse transition variance for every pixel
B. The noise that was added at each timestep
C. The clean image directly from in one step
D. The joint distribution of all intermediate latents simultaneously

43 A transformer-based LLM uses self-attention with sequence length . Why does doubling the context length roughly quadruple the attention computation cost?

LLMs Hard
A. Because positional encodings grow exponentially with
B. Because the feed-forward layers scale with
C. Because embedding dimension must double with context
D. Because the attention matrix has size , so cost scales as

44 Prompt tuning (soft prompts) differs fundamentally from full fine-tuning. Which statement most accurately captures this difference?

Prompt Tuning Hard
A. Prompt tuning modifies only the final output softmax layer
B. Prompt tuning learns continuous embedding vectors while keeping model weights frozen
C. Prompt tuning requires retraining the tokenizer from scratch
D. Prompt tuning updates all model weights but freezes embeddings

45 A variational autoencoder (VAE) optimizes the Evidence Lower Bound (ELBO). The ELBO contains a reconstruction term and a KL-divergence term. What role does the KL term play?

How generative models work Hard
A. It enforces adversarial balance between two networks
B. It removes noise added during the diffusion forward pass
C. It maximizes reconstruction fidelity of decoded samples
D. It regularizes the approximate posterior toward the prior over latents

46 Mode collapse is a well-known GAN failure. Which description best characterizes what mode collapse actually is?

GANs Hard
A. The generator produces limited, repetitive outputs ignoring the data's diversity
B. The discriminator perfectly memorizes the training set
C. The generator outputs pure noise indistinguishable from static
D. The loss oscillates without ever decreasing

47 A company deploys an LLM that occasionally reproduces copyrighted text verbatim from its training data. Which mitigation directly targets this specific risk rather than a different ethical concern?

Ethics and Responsible Use of Generative AI Hard
A. Lowering the sampling temperature at inference
B. Increasing the model's context window size
C. Adding a demographic fairness constraint to the loss function
D. Applying differential privacy or memorization-reduction techniques during training

48 Consider two prompts for a summarization task. Prompt A says "Summarize this." Prompt B specifies audience, length, format, and tone. From a prompt-engineering standpoint, why does Prompt B typically yield more reliable output?

Key elements of a good prompt Hard
A. It reduces the model's parameter count temporarily
B. It forces the model into a deterministic decoding mode
C. It bypasses the model's safety filters for richer output
D. It constrains the output space by providing explicit context and constraints

49 The "Chain-of-Thought" prompting pattern improves performance on multi-step reasoning tasks. What is the primary mechanism behind this improvement?

Prompt Patterns Hard
A. It compresses the prompt to fit more context
B. It increases the model's training data at inference time
C. It allocates intermediate tokens that let the model decompose reasoning steps
D. It disables the softmax to allow deterministic answers

50 Temperature and top- (nucleus) sampling both control randomness. Setting temperature to a very low value (near 0) has what effect on generation?

LLMs Hard
A. It increases hallucination by amplifying rare tokens
B. It flattens the probability distribution toward uniform sampling
C. It expands the vocabulary considered at each step
D. It sharpens the distribution, approaching greedy (near-deterministic) decoding

51 Which distinction most accurately separates discriminative models from generative models?

Fundamentals of Generative AI Hard
A. Generative models only work on images while discriminative models work on text
B. Generative models estimate or ; discriminative models estimate
C. Generative models cannot be used for classification under any circumstances
D. Discriminative models require more parameters by definition

52 Classifier-free guidance is widely used in text-to-image diffusion models. What does it accomplish?

Diffusion Hard
A. It interpolates between conditional and unconditional predictions to strengthen prompt adherence
B. It removes the need for a text encoder entirely
C. It replaces the reverse diffusion process with a single forward pass
D. It trains a separate classifier to grade image quality post-hoc

53 An autoregressive language model factorizes the probability of a sequence. Which factorization does it use?

Overview of language models Hard
A.
B. predicting backward only
C. assuming independence
D.

54 A business wants to automate first-draft generation of marketing copy while ensuring factual product claims remain accurate. Which architecture best addresses the accuracy requirement?

Industrial applications (content creation, automation) Hard
A. Prompt tuning alone with no external data source
B. A GAN trained on past marketing images
C. Retrieval-Augmented Generation (RAG) grounding output in a verified product database
D. A larger base model with higher temperature sampling

55 The "Persona" prompt pattern instructs the model to adopt a specific role (e.g., "Act as a senior security auditor"). What is the most accurate account of why this can improve outputs?

Prompt Patterns Hard
A. It gives the model access to external databases for that role
B. It permanently alters the model's weights toward that domain
C. It conditions generation toward tokens statistically associated with that role's language and expertise
D. It disables generation of any content outside the role

56 A generative model trained on internet data exhibits biased associations between certain professions and genders. Which statement correctly diagnoses the root cause?

Ethics and Responsible Use of Generative AI Hard
A. The model's architecture is inherently biased regardless of data
B. The bias reflects statistical patterns present in the training corpus
C. The bias is introduced solely by the tokenizer
D. The bias arises only from the decoding temperature setting

57 In few-shot prompting, providing in-context examples improves performance without any weight updates. What is the best explanation for this capability?

Fundamentals of prompt Hard
A. The examples are stored in a persistent memory bank across sessions
B. The examples fine-tune the model's parameters during inference
C. The examples reduce the model's vocabulary to relevant tokens
D. The model performs in-context learning, inferring the task pattern from the provided examples

58 Two teams achieve very different accuracy on the same reasoning benchmark using the identical model. Which factor from prompt engineering most plausibly explains this gap?

Importance of Prompt Engineering Hard
A. One team used a physically faster GPU
B. Differences in prompt structure, examples, and instruction clarity
C. Different color themes in their code editors
D. Random variation in the model's fixed weights between teams

59 Wasserstein GAN (WGAN) replaces the original loss with the Earth Mover's distance. Why is this often more stable than the Jensen-Shannon divergence used implicitly in vanilla GANs?

GANs Hard
A. It guarantees zero mode collapse in all cases
B. It eliminates the need for a discriminator entirely
C. It provides meaningful gradients even when real and generated distributions barely overlap
D. It removes randomness from the generator input

60 Comparing generative approaches: GANs, VAEs, and diffusion models. Which pairing of model with its most characteristic training signal is correct?

How generative models work Hard
A. GAN: noise-prediction; VAE: adversarial game; Diffusion: ELBO only
B. GAN: adversarial min-max game; VAE: ELBO maximization; Diffusion: denoising/noise-prediction objective
C. GAN: reconstruction MSE; VAE: min-max game; Diffusion: contrastive loss
D. GAN: ELBO; VAE: adversarial game; Diffusion: reconstruction only