AIF-C01 practice questions 251–260

1. Question 251 · 417 in bank

   A company is using an Amazon Nova Canvas model to generate images. The model generates images successfully. The company needs to prevent the model from including specific items in the generated images. Which solution will meet this requirement?

   • AUse a higher temperature value.
   • BUse a more detailed prompt.
   • CUse a negative prompt.
   • DUse another foundation model (FM).

   Show answer

   Answer: C

   Next question

2. Question 252 · 417 in bank

   A company wants to label training datasets by using human feedback to fine-tune a foundation model (FM). The company does not want to develop labeling applications or manage a labeling workforce. Which AWS service or feature meets these requirements?

   • AAmazon SageMaker Data Wrangler
   • BAmazon SageMaker Ground Truth Plus
   • CAmazon Transcribe
   • DAmazon Macie

   Show answer

   Answer: B

   Next question

3. Question 253 · 417 in bank

   An online media streaming company wants to give its customers the ability to perform natural language-based image search and filtering. The company needs a vector database that can help with similarity searches and nearest neighbor queries. Which AWS service meets these requirements?

   • AAmazon Comprehend
   • BAmazon Personalize
   • CAmazon Polly
   • DAmazon OpenSearch Service

   Show answer

   Answer: D

   Next question

4. Question 254 · 417 in bank

   A company is building a generative AI tool. The company will use internal documents to customize a foundation model (FM). Which approach will meet this requirement?

   • AClassification
   • BContinued pre-training
   • CDistillation
   • DRegression

   Show answer

   Answer: B

   Next question

5. Question 255 · 417 in bank

   A company is monitoring a predictive model by using Amazon SageMaker Model Monitor. The company notices data drift beyond a defined threshold. The company wants to mitigate a potentially adverse impact on the predictive model. Which solution will meet these requirements?

   • ARestart the SageMaker AI endpoint.
   • BAdjust the monitoring sensitivity.
   • CRe-train the model with fresh data.
   • DSet up experiments tracking.

   Show answer

   Answer: C

   Next question

6. Question 256 · 417 in bank

   A financial company uses a generative AI model to assign credit limits to new customers. The company wants to make the decision-making process of the model more transparent to its customers. Which solution meets these requirements?

   • AUse a rule-based system instead of an ML model.
   • BApply explainable AI techniques to show customers which factors influenced the model’s decision.
   • CDevelop an interactive UI for customers and provide clear technical explanations about the system.
   • DIncrease the accuracy of the model to reduce the need for transparency.

   Show answer

   Answer: B

   Next question

7. Question 257 · 417 in bank

   A company deployed a model to production. After 4 months, the model inference quality degraded. The company wants to receive a notification if the model inference quality degrades. The company also wants to ensure that the problem does not happen again. Which solution will meet these requirements?

   • ARetrain the model. Monitor model drift by using Amazon SageMaker Clarify.
   • BRetrain the model. Monitor model drift by using Amazon SageMaker Model Monitor.
   • CBuild a new model. Monitor model drift by using Amazon SageMaker Feature Store.
   • DBuild a new model. Monitor model drift by using Amazon SageMaker JumpStart.

   Show answer

   Answer: B

   Next question

8. Question 258 · 417 in bank

   Which option is an example of unsupervised learning?

   • AA model that groups customers based on their purchase history
   • BA model that classifies images as dogs or cats
   • CA model that predicts a house’s price based on various features
   • DA model that learns to play chess by using trial and error

   Show answer

   Answer: A

   Next question

9. Question 259 · 417 in bank

   A company is evaluating several large language models (LLMs) for a text summarization task. The company needs to select a metric to evaluate the quality of the summaries that the LLMs generate. Which metric will meet this requirement?

   • ARecall
   • BArea under the ROC curve (AUC)
   • CRecall-Oriented Understudy for Gisting Evaluation (ROUGE)
   • DMean squared error (MSE)

   Show answer

   Answer: C

   Next question

10. Question 260 · 417 in bank

    A research group wants to test different generative AI models to create research papers. The research group has defined a prompt and needs a method to assess the models’ output. The research group wants to use a team of scientists to perform the output assessments. Which solution will meet these requirements?

    • AUse automatic evaluation on Amazon Personalize.
    • BUse content moderation on Amazon Rekognition.
    • CUse model evaluation on Amazon Bedrock.
    • DUse sentiment analysis on Amazon Comprehend.

    Show answer

    Answer: C

    Next question

Keyboard:J Kmove between questionsA–Dselect an answerRshow or hide the answer← →change page

AIF-C01 practice, question 251. 417 questions available.