AIF-C01 practice questions 211–220

1. Question 211 · 417 in bank

   A company uses a third-party model on Amazon Bedrock to analyze confidential documents. The company is concerned about data privacy. Which statement describes how Amazon Bedrock protects data privacy?

   • AUser inputs and model outputs are anonymized and shared with third-party model providers.
   • BUser inputs and model outputs are not shared with any third-party model providers.
   • CUser inputs are kept confidential, but model outputs are shared with third-party model providers.
   • DUser inputs and model outputs are redacted before the inputs and outputs are shared with third-party model providers.

   Show answer

   Answer: B

   Next question

2. Question 212 · 417 in bank

   An animation company wants to provide subtitles for its content. Which AWS service meets this requirement?

   • AAmazon Comprehend
   • BAmazon Polly
   • CAmazon Transcribe
   • DAmazon Translate

   Show answer

   Answer: C

   Next question

3. Question 213 · 417 in bank

   An ecommerce company wants to group customers based on their purchase history and preferences to personalize the user experience of the company's application. Which ML technique should the company use?

   • AClassification
   • BClustering
   • CRegression
   • DContent generation

   Show answer

   Answer: B

   Next question

4. Question 214 · 417 in bank

   A company wants to control employee access to publicly available foundation models (FMs). Which solution meets these requirements?

   • AAnalyze cost and usage reports in AWS Cost Explorer.
   • BDownload AWS security and compliance documents from AWS Artifact.
   • CConfigure Amazon SageMaker JumpStart to restrict discoverable FMs.
   • DBuild a hybrid search solution by using Amazon OpenSearch Service.

   Show answer

   Answer: C

   Next question

5. Question 215 · 417 in bank

   A company has set up a translation tool to help its customer service team handle issues from customers around the world. The company wants to evaluate the performance of the translation tool. The company sets up a parallel data process that compares the responses from the tool to responses from actual humans. Both sets of responses are generated on the same set of documents. Which strategy should the company use to evaluate the translation tool?

   • AUse the Bilingual Evaluation Understudy (BLEU) score to estimate the absolute translation quality of the two methods.
   • BUse the Bilingual Evaluation Understudy (BLEU) score to estimate the relative translation quality of the two methods.
   • CUse the BERTScore to estimate the absolute translation quality of the two methods.
   • DUse the BERTScore to estimate the relative translation quality of the two methods.

   Show answer

   Answer: B

   Next question

6. Question 216 · 417 in bank

   An AI practitioner wants to generate more diverse and more creative outputs from a large language model (LLM). How should the AI practitioner adjust the inference parameter?

   • AIncrease the temperature value.
   • BDecrease the Top K value.
   • CIncrease the response length.
   • DDecrease the prompt length.

   Show answer

   Answer: A

   Next question

7. Question 217 · 417 in bank

   A company has developed custom computer vision models. The company needs a user-friendly interface for data labeling to minimize model mistakes on new real-world data. Which AWS service, feature, or tool meets these requirements?

   • AAmazon SageMaker Ground Truth
   • BAmazon SageMaker Canvas
   • CAmazon Bedrock playground
   • DAmazon Bedrock Agents

   Show answer

   Answer: A

   Next question

8. Question 218 · 417 in bank

   Select 2

   A company is integrating AI into its employee recruitment and hiring solution. The company wants to mitigate bias risks and ensure responsible AI practices while prioritizing equitable hiring decisions. Which core dimensions of responsible AI should the company consider? (Choose two.)

   • AFairness
   • BTolerance
   • CFlexibility
   • DOpen source
   • ETransparency

   Show answer

   Answer: AE

   Next question

9. Question 219 · 417 in bank

   A financial company has deployed an ML model to predict customer churn. The model has been running in production for 1 week. The company wants to evaluate how accurately the model predicts churn compared to actual customer behavior. Which metric meets these requirements?

   • ARoot mean squared error (RMSE)
   • BReturn on investment (ROI)
   • CF1 score
   • DBilingual Evaluation Understudy (BLEU) score

   Show answer

   Answer: C

   Next question

10. Question 220 · 417 in bank

    A company has a generative AI application that uses a pre-trained foundation model (FM) on Amazon Bedrock. The company wants the FM to include more context by using company information. Which solution meets these requirements MOST cost-effectively?

    • AUse Amazon Bedrock Knowledge Bases.
    • BChoose a different FM on Amazon Bedrock.
    • CUse Amazon Bedrock Agents.
    • DDeploy a custom model on Amazon Bedrock.

    Show answer

    Answer: A

    Next question

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

AIF-C01 practice, question 211. 417 questions available.