AWS Certified AI Practitioner (AIF-C01) — Question 173

A company wants to fine-tune a foundation model (FM) to answer questions for a specific domain. The company wants to use instruction-based fine-tuning.

How should the company prepare the training data?

Answer options

• A. Gather company internal documents and industry-specific materials. Merge the documents and materials into a single file.
• B. Collect external company reviews from various online sources. Manually label each review as either positive or negative.
• C. Create pairs of questions and answers that specifically address topics related to the company's industry domain.
• D. Create few-shot prompts to instruct the model to answer only domain knowledge.

Correct answer: C

Explanation

The correct answer is C because creating question-answer pairs directly related to the industry ensures that the model learns the specific information it needs to function effectively. Option A is not sufficient as it lacks direct question-answer relevance. Option B is focused on sentiment analysis, which does not align with fine-tuning for domain-specific questions. Option D, while useful, does not provide the structured training data necessary for effective instruction-based fine-tuning.