AWS Certified AI Practitioner (AIF-C01)

The AWS Certified AI Practitioner (AIF-C01) were last updated on today.

Viewing page 6 out of 24 pages.
Viewing questions 26-30 out of 120 questions

Disclaimers:

- ExamTopics website is not related to, affiliated with, endorsed or authorized by Amazon.and Azure
- Trademarks, certification & product names are used for reference only and belong to Amazon.and Azure

Topic 1 - Exam A

Question #26 Topic 1

A company wants to create a new solution by using AWS Glue. The company has minimal programming experience with AWS Glue. Which AWS service can help the company use AWS Glue?

A Amazon Q Developer
B AWS Config
C Amazon Personalize
D Amazon Comprehend

Suggested Answer: A
NOTE: 在这个情境中，公司想要使用AWS Glue创建一个新的解决方案，但缺乏AWS Glue的编程经验。Amazon Q（可能指的是Amazon Q for Developers）是一种可以帮助开发人员快速上手和使用的工具或服务，它能够提供指导和自动化功能，以帮助解决缺乏经验的问题。

Question #27 Topic 1

A company wants to implement a large language model (LLM) based chatbot to provide customer service agents with real-time contextual responses to customers' inquiries. The company will use the company's policies as the knowledge base. Which solution will meet these requirements MOST cost-effectively?

A Retrain the LLM on the company policy data.
B Fine-tune the LLM on the company policy data.
C Implement Retrieval Augmented Generation (RAG) for in-context responses.
D Use pre-training and data augmentation on the company policy data.

Suggested Answer: C
NOTE: -

Question #28 Topic 1

A company is using Retrieval Augmented Generation (RAG) with Amazon Bedrock and Stable Diffusion to generate product images based on text descriptions. The results are often random and lack specific details. The company wants to increase the specificity of the generated images. Which solution meets these requirements?

A Increase the number of generation steps.
B Use the MASK_IMAGE_BLACK mask source option.
C Increase the classifier-free guidance (CFG) scale.
D Increase the prompt strength.

Suggested Answer: C
NOTE: 在给定的选项中，增加分类器自由引导（CFG）缩放可以提高生成图像的具体性。CFG是一种技术，通过调整CFG缩放参数，模型会更加依赖于提供的提示，从而生成更符合要求的图像。

Question #29 Topic 1

A company has fine-tuned a large language model (LLM) to answer questions for a help desk. The company wants to determine if the fine-tuning has enhanced the model's accuracy. Which metric should the company use for the evaluation?

A Precision
B Time to first token
C F1 score
D Word error rate

Suggested Answer: C
NOTE: F1 score is the appropriate metric to evaluate the accuracy of the fine-tuned model, as it considers both precision and recall, providing a balanced measure of the model's performance.

Question #30 Topic 1

Which prompting technique can protect against prompt injection attacks?

A Adversarial prompting
B Zero-shot prompting
C Least-to-most prompting
D Chain-of-thought prompting

Suggested Answer: A
NOTE: The question asks about a prompting technique that can protect against prompt injection attacks. Among the options provided, Adversarial prompting (Option A) is known for its ability to defend against adversarial attacks by generating responses that are robust and less susceptible to such attacks, including prompt injection attacks.