Q97 — AWS AIF-C01 Ch.3

Question 97 of 100 | ← Chapter 3

An accounting firm wants to implement a large language model (LLM) to automate document processing. The firm must do so responsibly to avoid potential risks. What should the company do when developing and deploying the LLM? (Choose TWO.)

• A. Include fairness metrics in model evaluation. ✓
• B. Adjust the model’s temperature parameter.
• C. Modify training data to reduce bias. ✓
• D. Avoid overfitting the training data.
• E. Apply prompt engineering techniques.

Correct Answer: A. Include fairness metrics in model evaluation., C. Modify training data to reduce bias.

Explanation

This question tests responsible LLM deployment practices. Including fairness metrics in evaluation ensures equitable outcomes. Modifying training data to reduce bias proactively mitigates discriminatory behavior. Adjusting temperature affects output randomness—not responsibility. Avoiding overfitting is a standard ML best practice but not uniquely tied to responsible AI. Prompt engineering improves output quality but does not directly address fairness or bias mitigation.