A company is using a large language model (LLM) on Amazon Bedrock to build a chatbot. The chatbot processes customer support requests. To resolve a request, the customer and the chatbot must interact a few times.Which solution gives the LLM the ability to use content from previous customer messages?

Add messages to the model prompt.

Turn on model invocation logging to collect messages.

Add messages to the model prompt.

Use Amazon Personalize to save conversation history.

Use Provisioned Throughput for the LLM.

An ML research team develops custom ML models. The model artifacts are shared with other teams for integration into products and services. The ML team retains the model training code and data. The ML team wants to builk a mechanism that the ML team can use to audit models.Which solution should the ML team use when publishing the custom ML models?

Create Amazon SageMaker Model Cards with Intended uses and training and inference details.

Create documents with the relevant information. Store the documents in Amazon S3.

Use AWS A] Service Cards for transparency and understanding models.

Create Amazon SageMaker Model Cards with Intended uses and training and inference details.

Create model training scripts. Commit the model training scripts to a Git repository.

A company wants to create a chatbot that answers questions about human resources policies. The company is using a large language model (LLM) and has a large digital documentation base.Which technique should the company use to optimize the generated responses?

Use Retrieval Augmented Generation (RAG).

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?

Large language model (LLM) hallucinations

Which scenario represents a practical use case for generative AI?

Employing a chatbot to provide human-like responses to customer queries in real time

Using an ML model to forecast product demand

Employing a chatbot to provide human-like responses to customer queries in real time

Using an analytics dashboard to track website traffic and user behavior

Implementing a rule-based recommendation engine to suggest products to customers

Which technique breaks a complex task into smaller subtasks that are sent sequentially to a large language model (LLM)?

Retrieval Augmented Generation (RAG)

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?

Ensure that the data is balanced and collected from a diverse group.

Use data from only customers who match the demography of the company's overall customer base.

Collect data from customers who have a past purchase history.

Ensure that the data is balanced and collected from a diverse group.

Ensure that the data is from a publicly available dataset.

Which option is a characteristic of AI governance frameworks for building trust and deploying human-centered AI technologies?

Developing policies and guidelines for data, transparency, responsible AI, and compliance\

Expanding initiatives across business units to create long-term business value

Ensuring alignment with business standards, revenue goals, and stakeholder expectations

Overcoming challenges to drive business transformation and growth

Developing policies and guidelines for data, transparency, responsible AI, and compliance\

A media company wants to analyze viewer behavior and demographics to recommend personalized content. The company wants to deploy a customized ML model in its production environment. The company also wants to observe if the model quality drifts over time.Which AWS service or feature meets these requirements?

Amazon Rekognition: This service is designed for image and video analysis, such as object detection, facial recognition, and text extraction. It is not suited for deploying custom ML models or monitoring model quality drift.

Amazon SageMaker Clarify: This feature helps detect bias in ML models and explains model predictions. While it addresses fairness and interpretability, it does not specifically focus on monitoring model quality drift over time in production.

Amazon Comprehend: This is a natural language processing (NLP) service for extracting insights from text, such as sentiment analysis or entity recognition. It does not support deploying custom ML models or monitoring model performance drift.

Amazon SageMaker Model Monitor: This feature is part of Amazon SageMaker and is specifically designed to monitor ML models in production. It tracks metrics such as data drift, model drift, and performance degradation over time, alerting users when issues are detected.Exact ExtractReference: According to the AWS documentation on Amazon SageMaker, ''Amazon SageMaker Model Monitor allows you to detect and remediate data and model quality issues in production. It continuously monitors the performance of deployed models, capturing data and model predictions to detect deviations from expected behavior, such as data drift or model performance degradation.'' (Source: AWS SageMaker Documentation - Model Monitoring, https://docs.aws.amazon.com/sagemaker/latest/dg/model-monitor.html).This directly aligns with the requirement to observe model quality drift, making Amazon SageMaker Model Monitor the correct choice.

A bank is fine-tuning a large language model (LLM) on Amazon Bedrock to assist customers with questions about their loans. The bank wants to ensure that the model does not reveal any private customer data.Which solution meets these requirements?

Remove personally identifiable information (PII) from the customer data before fine-tuning the LLM.

Increase the Top-K parameter of the LLM.

Store customer data in Amazon S3. Encrypt the data before fine-tuning the LLM.

Amazon Bedrock Guardrails: Guardrails in Amazon Bedrock allow users to define policies to filter harmful or sensitive content in model inputs and outputs. While useful for real-time content moderation, they do not address the risk of private data being embedded in the model during fine-tuning, as the model could still memorize sensitive information.

Remove personally identifiable information (PII) from the customer data before fine-tuning the LLM: Removing PII (e.g., names, addresses, account numbers) from the training dataset ensures that the model does not learn or memorize sensitive customer data, reducing the risk of data leakage. This is a proactive and effective approach to data privacy during model training.

Increase the Top-K parameter of the LLM: The Top-K parameter controls the randomness of the model's output by limiting the number of tokens considered during generation. Adjusting this parameter affects output diversity but does not address the privacy of customer data embedded in the model.

Store customer data in Amazon S3. Encrypt the data before fine-tuning the LLM: Encrypting data in Amazon S3 protects data at rest and in transit, but during fine-tuning, the data is decrypted and used to train the model. If PII is present, the model could still learn and potentially expose it, so encryption alone does not solve the problem.Exact ExtractReference: AWS emphasizes data privacy in AI/ML workflows, stating, ''To protect sensitive data, you can preprocess datasets to remove personally identifiable information (PII) before using them for model training. This reduces the risk of models inadvertently learning or exposing sensitive information.'' (Source: AWS Best Practices for Responsible AI, https://aws.amazon.com/machine-learning/responsible-ai/). Additionally, the Amazon Bedrock documentation notes that users are responsible for ensuring compliance with data privacy regulations during fine-tuning (https://docs.aws.amazon.com/bedrock/latest/userguide/model-customization.html).Removing PII before fine-tuning is the most direct and effective way to prevent the model from revealing private customer data, making B the correct answer.

An AI practitioner needs to improve the accuracy of a natural language generation model. The model uses rapidly changing inventory data.Which technique will improve the model's accuracy?

Retrieval Augmented Generation (RAG)

Transfer learning: This involves pre-training a model on a large dataset and fine-tuning it for a specific task. While effective for general model improvement, it does not specifically address the challenge of incorporating rapidly changing inventory data into the model's responses.

Federated learning: This technique trains models across decentralized devices while keeping data localized, primarily for privacy purposes. It is not designed to handle rapidly changing data or improve NLG model accuracy in this context.

Retrieval Augmented Generation (RAG): RAG combines a language model with a retrieval mechanism that fetches relevant, up-to-date information (e.g., inventory data) from an external source during inference. This is ideal for scenarios with dynamic data, as it ensures the model's responses are grounded in the latest information, improving accuracy.

One-shot prompting: This involves providing a single example to guide the model's output. While useful for specific tasks, it does not scale well for rapidly changing data or ensure consistent accuracy with dynamic inventory updates.Exact ExtractReference: According to AWS documentation on generative AI techniques, ''Retrieval Augmented Generation (RAG) enhances large language models by retrieving relevant documents or data at inference time, enabling the model to generate accurate and contextually relevant responses, especially for dynamic or frequently updated datasets.'' (Source: AWS Generative AI Glossary, https://aws.amazon.com/what-is/retrieval-augmented-generation/). This directly addresses the need for accuracy with rapidly changing inventory data.RAG is the most suitable technique for this scenario, as it allows the model to access and incorporate the latest inventory data, making C the correct answer.

A manufacturing company uses AI to inspect products and find any damages or defects.Which type of AI application is the company using?

Natural language processing (NLP)

Amazon AIF-C01 Practice Test 4 - Free Online Exam Prep & Questions

A company is developing a mobile ML app that uses a phone's camera to diagnose and treat insect bites. The company wants to train an image classification model by using a diverse dataset of insect bite photos from different genders, ethnicities, and geographic locations around the world.

Which principle of responsible Al does the company demonstrate in this scenario?

Become a Premium Member for full access

Unlock Premium Member

Amazon AIF-C01 Practice Test 4

Question

Amazon AIF-C01 Practice Tests

Practice Tests