AWS Certified AI Practitioner (AIF-C01) — Question 59

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

Answer options

• A. Include fairness metrics for model evaluation.
• B. Adjust the temperature parameter of the model.
• C. Modify the training data to mitigate bias.
• D. Avoid overfitting on the training data.
• E. Apply prompt engineering techniques.

Correct answer: A, C

Explanation

Including fairness metrics for model evaluation (A) ensures that the model is assessed for biases and fairness, which is crucial for responsible deployment. Modifying the training data to mitigate bias (C) directly addresses potential biases in the model, promoting ethical use. Options B, D, and E, while important for model performance, do not specifically address the responsible development and deployment concerns related to bias and fairness.