AIF-C01 practice questions 91–100

1. Question 91 · 417 in bank

   Select 2

   An ecommerce company wants to build a solution to determine customer sentiments based on written customer reviews of products. Which AWS services meet these requirements? (Choose two.)

   • AAmazon Lex
   • BAmazon Comprehend
   • CAmazon Polly
   • DAmazon Bedrock
   • EAmazon Rekognition

   Show answer

   Answer: BD

   Explanation

   Amazon Comprehend is a natural language processing (NLP) service that uses machine learning to uncover insights and relationships in text. It offers sentiment analysis capabilities out-of-the-box, which can directly determine the sentiment (positive, negative, neutral, or mixed) expressed in customer reviews. Amazon Bedrock is a fully managed service that makes foundation models accessible with simple API calls. It allows you to build generative AI applications for various use cases, including sentiment analysis. By providing customer reviews as input prompts, you can use Bedrock to generate sentiment labels or scores.

   Source: Adapted from community discussion — taka5094

   Next question

2. Question 92 · 417 in bank

   A company wants to use large language models (LLMs) with Amazon Bedrock to develop a chat interface for the company's product manuals. The manuals are stored as PDF files. Which solution meets these requirements MOST cost-effectively?

   • AUse prompt engineering to add one PDF file as context to the user prompt when the prompt is submitted to Amazon Bedrock.
   • BUse prompt engineering to add all the PDF files as context to the user prompt when the prompt is submitted to Amazon Bedrock.
   • CUse all the PDF documents to fine-tune a model with Amazon Bedrock. Use the fine-tuned model to process user prompts.
   • DUpload PDF documents to an Amazon Bedrock knowledge base. Use the knowledge base to provide context when users submit prompts to Amazon Bedrock.

   Show answer

   Answer: D

   Explanation

   Upload PDF documents to an Amazon Bedrock knowledge base. Use the knowledge base to provide context when users submit prompts to Amazon Bedrock: While this could be an efficient solution, it may not be as cost-effective as using prompt engineering with just the necessary context per query. Building and maintaining a knowledge base could incur additional costs, especially if the company only needs a temporary context for each query.

   Source: Adapted from community discussion — Jessiii

   Next question

3. Question 93 · 417 in bank

   A social media company wants to use a large language model (LLM) for content moderation. The company wants to evaluate the LLM outputs for bias and potential discrimination against specific groups or individuals. Which data source should the company use to evaluate the LLM outputs with the LEAST administrative effort?

   • AUser-generated content
   • BModeration logs
   • CContent moderation guidelines
   • DBenchmark datasets

   Show answer

   Answer: D

   Explanation

   Benchmark datasets: Benchmark datasets are specifically designed for evaluating models on specific tasks, including fairness and bias. These datasets typically include a wide range of content and scenarios designed to assess how well the model handles various forms of bias or discrimination. Using these datasets will provide the least administrative effort because they are pre-structured and widely recognized for evaluating model behavior across a variety of contexts.

   Source: Adapted from community discussion — Jessiii

   Next question

4. Question 94 · 417 in bank

   A company wants to use a pre-trained generative AI model to generate content for its marketing campaigns. The company needs to ensure that the generated content aligns with the company's brand voice and messaging requirements. Which solution meets these requirements?

   • AOptimize the model's architecture and hyperparameters to improve the model's overall performance.
   • BIncrease the model's complexity by adding more layers to the model's architecture.
   • CCreate effective prompts that provide clear instructions and context to guide the model's generation.
   • DSelect a large, diverse dataset to pre-train a new generative model.

   Show answer

   Answer: C

   Explanation

   C. Create effective prompts that provide clear instructions and context to guide the model's generation. Prompt engineering is a crucial technique to ensure that a pre-trained generative AI model generates content that aligns with the company's brand voice and messaging requirements. By carefully crafting prompts, you can guide the model to produce specific, relevant, and on-brand content.

   Source: Adapted from community discussion — eesa

   Next question

5. Question 95 · 417 in bank

   Select 2

   A loan company is building a generative AI-based solution to offer new applicants discounts based on specific business criteria. The company wants to build and use an AI model responsibly to minimize bias that could negatively affect some customers. Which actions should the company take to meet these requirements? (Choose two.)

   • ADetect imbalances or disparities in the data.
   • BEnsure that the model runs frequently.
   • CEvaluate the model's behavior so that the company can provide transparency to stakeholders.
   • DUse the Recall-Oriented Understudy for Gisting Evaluation (ROUGE) technique to ensure that the model is 100% accurate.
   • EEnsure that the model's inference time is within the accepted limits.

   Show answer

   Answer: AC

   Next question

6. Question 96 · 417 in bank

   A company is using a pre-trained large language model (LLM) to build a chatbot for product recommendations. The company needs the LLM outputs to be short and written in a specific language. Which solution will align the LLM response quality with the company's expectations?

   • AAdjust the prompt.
   • BChoose an LLM of a different size.
   • CIncrease the temperature.
   • DIncrease the Top K value.

   Show answer

   Answer: A

   Explanation

   B not correct - The size of LLM may not affect the size of the output. C not correct - Temperature controls the creativity of the output, not size of the output. D not correct - Top-K controls number of next possible tokens, not size of the output. A is correct - In the prompt itself we can control various attributes of the output like size, language etc.

   Source: Adapted from community discussion — 0c2d840

   Next question

7. Question 97 · 417 in bank

   A company is using an Amazon Bedrock base model to summarize documents for an internal use case. The company trained a custom model to improve the summarization quality. Which action must the company take to use the custom model through Amazon Bedrock?

   • APurchase Provisioned Throughput for the custom model.
   • BDeploy the custom model in an Amazon SageMaker endpoint for real-time inference.
   • CRegister the model with the Amazon SageMaker Model Registry.
   • DGrant access to the custom model in Amazon Bedrock.

   Show answer

   Answer: A

   Explanation

   B, and C, CANNOT be as the question is clear: "..using an Amazon Bedrock.. through Amazon BedRock" , in short SageMaker is out of the picture in this case. we are talking about a customize Bedrock Model.. so .. A is the only possible answer, we are not deploying a custom model in bedrock, we are using a bedrock customised model.. and in that case you have to pay the premium... as per this link: https://docs.aws.amazon.com/bedrock/latest/userguide/prov-throughput.html ...If you customized a model, you must purchase Provisioned Throughput to be able to use it

   Source: Adapted from community discussion — fed6485

   References

   • AWS documentation
   • AWS documentation
   • AWS documentation
   • AWS documentation
   • AWS documentation

   Next question

8. Question 98 · 417 in bank

   A company needs to choose a model from Amazon Bedrock to use internally. The company must identify a model that generates responses in a style that the company's employees prefer. What should the company do to meet these requirements?

   • AEvaluate the models by using built-in prompt datasets.
   • BEvaluate the models by using a human workforce and custom prompt datasets.
   • CUse public model leaderboards to identify the model.
   • DUse the model InvocationLatency runtime metrics in Amazon CloudWatch when trying models.

   Show answer

   Answer: B

   Explanation

   B: Evaluate the models by using a human workforce and custom prompt datasets. Explanation: To determine which model generates responses in the style that the company's employees prefer, the company should evaluate the models using custom prompt datasets relevant to their specific use cases. Additionally, involving a human workforce ensures subjective aspects, like tone, style, and alignment with employee preferences, are effectively assessed.

   Source: Adapted from community discussion — Moon

   Next question

9. Question 99 · 417 in bank

   A student at a university is copying content from generative AI to write essays. Which challenge of responsible generative AI does this scenario represent?

   • AToxicity
   • BHallucinations
   • CPlagiarism
   • DPrivacy

   Show answer

   Answer: C

   Next question

10. Question 100 · 417 in bank

    A company needs to build its own large language model (LLM) based on only the company's private data. The company is concerned about the environmental effect of the training process. Which Amazon EC2 instance type has the LEAST environmental effect when training LLMs?

    • AAmazon EC2 C series
    • BAmazon EC2 G series
    • CAmazon EC2 P series
    • DAmazon EC2 Trn series

    Show answer

    Answer: D

    References

    • AWS documentation

    Next question

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

AIF-C01 practice, question 91. 417 questions available.