QUESTION 41
A company needs to apply numerical transformations to a set of images to transpose and rotate the images. Which solution will meet these requirements in the MOST operationally efficient way?
A. Create a deep neural network by using the images as input.
B. Create an AWS Lambda function to perform the transformations.
C. Use an Amazon Bedrock large language model (LLM) with a high temperature.
D. Use AWS Glue Data Quality to make corrections to each image.
Correct Answer: B
QUESTION 42
A company is building a customer-facing generative Al assistant. The company wants to implement content filtering and safety controls to prevent hallucinations and to ensure safe and relevant responses. Which AWS solution will meet these requirements?
A. Amazon Rekognition content moderation
B. Amazon Bedrock Guardrails
C. Amazon Comprehend content filters
D. Amazon SageMaker Model Monitor
Correct Answer: B
QUESTION 43
An Al practitioner notices a large language model (LLM) is generating different responses for the same input across multiple invocations. Which risk of Al does this describe?
A. Hallucinations
B. Nondeterminism
C. Accuracy
D. Multimodality
Correct Answer: B
QUESTION 44
Which factor directly affects the performance and computational requirements of a large language model (LLM)?
A. Model size
B. Model provider
C. Training dataset size
D. Types of data that the model can process
Correct Answer: A
QUESTION 45
An AI practitioner notices a large language model (LLM) is generating different responses for the same input across multiple invocations. Which risk of AI does this describe?
A. Hallucinations
B. Nondeterminism
C. Accuracy
D. Multimodality
Correct Answer: B
QUESTION 46
Which factor directly affects the performance and computational requirements of a large language model (LLM)?
A. Model size
B. Model provider
C. Training dataset size
D. Types of data that the model can process
Correct Answer: A
QUESTION 47
A company uses Amazon SageMaker Al to generate article summaries in multiple languages. The company needs a metric to evaluate the quality of the summary translations in multiple languages. Which evaluation metric will meet these requirements?
A. Recall-Oriented Understudy for Gisting Evaluation (ROUGE)
B. Bilingual evaluation understudy (BLEU)
C. Area Under the ROC Curve (AUC)
D. Precision
Correct Answer: B
QUESTION 48
What is the primary purpose of system prompts in generative AI applications?
A. To authenticate user credentials to access responses from AI
B. To generate random responses by AI
C. To define the role and behavioral boundaries of AI
D. To compress output data from AI
Correct Answer: C
QUESTION 49
A company wants to develop an interpretable ML model to assess the risk of loan applications. Which type of ML model or algorithm will meet these requirements?
A. Deep learning model
B. Logistic regression model
C. K-means algorithm
D. Random cut forest algorithm
Correct Answer: B
QUESTION 50
A company is developing a new foundation model (FM) for multilingual text generation. The model must work across multiple languages and dialects. The model must adhere to the principles of responsible Al. Which model training process will meet these requirements?
A. Include prompt management templates in Amazon Bedrock to ensure that the output meets the principles of responsible AI.
B. Implement continued pre-training on a diverse multi-language and multi-dialect dataset.
C. Fine-tune separate models for each language and combine the models by using an Amazon Bedrock API.
D. Perform model distillation to use a single-language teacher model to teach each new language sequentially.
Correct Answer: B
QUESTION 51
A company stores customer personally identifiable information (PII) data. The company must store the PII data within the company’s AWS Region. Which aspect of governance does this describe?
A. Data mining
B. Data residency
C. Pre-training bias
D. Geolocation routing
Correct Answer: B
QUESTION 52
A company created an AI voice model that is based on a popular presenter. The company is using the model to create advertisements. However, the presenter did not consent to the use of his voice for the model. The presenter demands that the company stop the advertisements. Which challenge of working with generative Al does this scenario demonstrate?
A. Intellectual property (IP) infringement
B. Lack of transparency
C. Lack of fairness
D. Privacy infringement
Correct Answer: A
QUESTION 53
A company wants to increase employee productivity by using a generative Al solution to write code to test software applications. Which solution will meet these requirements with the LEAST operational effort?
A. Amazon Q Business
B. Amazon Bedrock Agents
C. Amazon Q Developer
D. Amazon SageMaker Clarify
Correct Answer: C
QUESTION 54
A company wants to develop an Al assistant to interact with external APIs. The Al assistant must provide application integration without the need for manually written custom code. Which Amazon Bedrock feature will meet these requirements?
A. Agents
B. Playgrounds
C. Prompt Management
D. Guardrails
Correct Answer: A
QUESTION 55
A company wants to customize a foundation model (FM) in Amazon Bedrock. The company will provide unlabeled data to familiarize the FM with specific input types. Which model training approach does this describe?
A. Distillation training
B. Prompt engineering
C. Fine-tuning
D. Continuous pre-training
Correct Answer: D
QUESTION 56
A company wants to detect unauthorized API actions for foundation models (FMs) in Amazon Bedrock. Which solution meets these requirements?
A. Configure AWS CloudTrail to monitor API activity.
B. Use AWS Trusted Advisor to monitor model input and output data.
C. Create Amazon QuickSight dashboards to monitor row-level safety.
D. Monitor user access by using Amazon Personalize.
Correct Answer: A
QUESTION 57
A company wants to use a large language model (LLM) to generate responses based on company data. Which strategy will meet this requirement?
A. Use first-party pre-trained models from Amazon Bedrock.
B. Use pre-trained open source models.
C. Fine-tune a custom model on company data.
D. Use pre-trained third-party models from Amazon Bedrock.
Correct Answer: C
QUESTION 58
A company is using Amazon Bedrock to develop an AI assistant. The AI assistant will respond to customer questions about the company’s products. The company conducts initial tests of the AI assistant. The company finds that the AI assistant’s responses do not represent the company well and might damage customer perception. The company needs a prompt engineering technique to improve the AI assistant’s responses so that the responses so that the responses better represent the company. Which solution will meet this requirement?
A. Use zero-shot prompting.
B. Use chain-of-thought (CoT) prompting.
C. Use Retrieval Augmented Generation (RAG).
D. Provide a persona and tone in the prompt.
Correct Answer: D
QUESTION 59
A company wants to create an ML model to predict customer satisfaction. The company needs fully automated model tuning. Which AWS service meets these requirements?
A. Amazon Personalize
B. Amazon SageMaker AI
C. Amazon Athena
D. Amazon Comprehend
Correct Answer: B
QUESTION 60
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?
A. Classification
B. Continued pre-training
C. Distillation
D. Regression
Correct Answer: B