A company is developing an ML model to predict customer churn.
Which evaluation metric will assess the model's performance on a binary classification task such as predicting churn?
A. F1 score
B. Mean squared error (MSE)
C. R-squared
D. Time used to train the model
Show Answer
Correct Answer: A
Explanation: Predicting customer churn is a binary classification problem. The F1 score is an appropriate evaluation metric because it measures performance based on both precision and recall, making it especially useful when classes may be imbalanced. The other options are regression metrics (MSE, R-squared) or not performance metrics (training time).
Question 121
A retail company wants to build an ML model to recommend products to customers. The company wants to build the model based on responsible practices.
Which practice should the company apply when collecting data to decrease model bias?
A. Use data from only customers who match the demographics of the company's overall customer base.
B. Collect data from customers who have a past purchase history.
C. Ensure that the data is balanced and collected from a diverse group.
D. Ensure that the data is from a publicly available dataset.
Show Answer
Correct Answer: C
Explanation: Reducing model bias requires training data that represents all relevant customer groups fairly. Ensuring the dataset is balanced and collected from a diverse population helps prevent overrepresentation or underrepresentation of specific demographics, leading to more equitable and responsible recommendations.
Question 122
Which term refers to the instructions given to foundation models (FMs) so that the FMs provide a more accurate response to a question?
A. Prompt
B. Direction
C. Dialog
D. Translation
Show Answer
Correct Answer: A
Explanation: In generative AI, a "prompt" is the set of instructions or input given to a foundation model to guide how it should respond. Well-designed prompts help the model understand the task and produce more accurate and relevant outputs. The other options do not specifically refer to this concept.
Question 123
A company needs to select a generative AI model to build an application. The application must provide responses to users in real time.
Which model characteristic should the company consider to meet these requirements?
A. Model complexity
B. Innovation speed
C. Inference speed
D. Training time
Show Answer
Correct Answer: C
Explanation: Real-time user responses require low latency between input and output. Inference speed measures how quickly a trained model can generate responses once it receives a prompt, making it the critical characteristic for real-time applications. Other factors like training time or model complexity do not directly determine response latency during use.
Question 124
A company wants to add generative AI functionality to its application by integrating a large language model (LLM). The responses from the LLM must be as deterministic and as stable as possible.
Which solution meets these requirements?
A. Configure the application to automatically set the temperature parameter to 0 when submitting the prompt to the LLM.
B. Configure the application to automatically add "make your response deterministic" at the end of the prompt before submitting the prompt to the LLM.
C. Configure the application to automatically add "make your response deterministic" at the beginning of the prompt before submitting the prompt to the LLM.
D. Configure the application to automatically set the temperature parameter to 1 when submitting the prompt to the LLM.
Show Answer
Correct Answer: A
Explanation: Setting the temperature parameter to 0 minimizes randomness in token selection, producing the most deterministic and stable outputs from an LLM. Prompting the model to be deterministic does not reliably enforce determinism, and a higher temperature (e.g., 1) increases variability.
Question 125
Which statement correctly describes embeddings in generative AI?
A. Embeddings represent data as high-dimensional vectors that capture semantic relationships.
B. Embeddings is a technique that searches data to find the most helpful information to answer natural language questions.
C. Embeddings reduce the hardware requirements of a model by using a less precise data type for the weights and activations.
D. Embeddings provide the ability to store and retrieve data for generative AI applications.
Show Answer
Correct Answer: A
Explanation: Embeddings encode data (such as text or images) into high-dimensional numerical vectors that preserve semantic meaning and relationships, so similar concepts are close together in vector space. This is the core definition of embeddings in generative AI. Option B describes retrieval/search, C describes quantization, and D describes storage mechanisms rather than embeddings themselves.
Question 126
In which stage of the generative AI model lifecycle are tests performed to examine the model's accuracy?
A. Deployment
B. Data selection
C. Fine-tuning
D. Evaluation
Show Answer
Correct Answer: D
Explanation: Tests that examine a model’s accuracy and overall performance are conducted during the Evaluation stage, where metrics are applied to assess how well the trained or fine-tuned model meets task objectives before deployment.
Question 127
An education company waftion. The application will give users the ability to enter text or provide a picture of a question. The application will respond with a written answer and an explanation of the written answer.
Which model type meets these requirements?
A. Computer vision model
B. Large multi-modal language model
C. Diffusion model
D. Text-to-speech model
Show Answer
Correct Answer: B
Explanation: The application must accept both text and image inputs (e.g., a photo of a question) and generate a written answer with an explanation. A large multi-modal language model can process multiple modalities such as text and images and produce coherent textual outputs, whereas the other options are limited to a single capability.
Question 128
A social media company wants to prevent users from posting discriminatory content on the company's application. The company wants to use Amazon Bedrock as part of the solution.
How can the company use Amazon Bedrock to meet these requirements?
A. Give users the ability to interact based on user preferences.
B. Block interactions related to predefined topics.
C. Restrict user conversations to predefined topics.
D. Provide a variety of responses to select from for user engagement.
Show Answer
Correct Answer: B
Explanation: Amazon Bedrock provides Guardrails that allow organizations to define denied or blocked topics such as hate speech or discriminatory content. By blocking interactions related to predefined topics, the platform can automatically filter or prevent discriminatory user content, meeting the requirement for content moderation.
Question 129
An ecommerce company is using a chatbot to automate the customer order submission process. The chatbot is powered by AI and is available to customers directly from the company's website 24 hours a day, 7 days a week.
Which option is an AI system input vulnerability that the company needs to resolve before the chatbot is made available?
A. Data leakage
B. Prompt injection
C. Large language model (LLM) hallucinations
D. Concept drift
Show Answer
Correct Answer: B
Explanation: Prompt injection is an AI system input vulnerability where malicious users craft inputs to override or manipulate the chatbot’s instructions or behavior. Because the chatbot is publicly accessible 24/7, attackers could exploit prompt injection to extract sensitive data, bypass safeguards, or perform unintended actions. The other options are risks or model limitations, but not specifically input vulnerabilities.
$19
Get all 397 questions with detailed answers and explanations
Instant download HTML + PDF delivered the moment payment clears.
Secure Stripe checkout we never see or store your card details.
7-day refund if files are defective see our refund policy.