AWS Certified AI Practitioner (AIF-C01) — Question 213

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?

Answer options

• A. Use Amazon Bedrock Guardrails.
• B. Remove personally identifiable information (PII) from the customer data before fine-tuning the LLM.
• C. Increase the Top-K parameter of the LLM.
• D. Store customer data in Amazon S3. Encrypt the data before fine-tuning the LLM.

Correct answer: B

Explanation

The correct answer is B because removing personally identifiable information (PII) ensures that no sensitive data is used in the model training process, thus protecting customer privacy. Option A, while helpful, does not specifically address the issue of preventing data leaks. Option C does not relate to data privacy and merely adjusts a parameter of the model. Option D involves encryption but does not prevent the original data from containing PII before fine-tuning.