Q56 — AWS AIF-C01 Ch.1

Question 56 of 100 | ← Chapter 1

A company uses Amazon Bedrock’s foundation models (FMs) for an AI-powered search tool. It aims to improve model accuracy by adapting the model using its own data. Which strategy successfully adapts the model?

• A. Providing labeled data with prompt and completion fields. ✓
• B. Preparing the training dataset as a .txt file containing multiple lines in .csv format.
• C. Purchasing Amazon Bedrock’s Provisioned Throughput.
• D. Training the model on academic journals and textbooks.

Correct Answer: A. Providing labeled data with prompt and completion fields.

Explanation

This question tests understanding of model fine-tuning strategies. To improve accuracy using proprietary data, supervised fine-tuning with labeled examples containing prompts and corresponding completions (Option A) is the standard and effective approach. Option B misrepresents proper data formatting requirements. Option C relates to throughput provisioning, not fine-tuning. Option D uses generic external sources, not company-specific data, and thus fails to achieve targeted adaptation.