Generative AI Leader Practice Question: Techniques to Improve Generative AI Model Output
A research lab is fine-tuning a large language model on a small dataset of medical records. They observe that the model overfits, memorizing specific patient details and producing outputs that violate privacy regulations. Which technique should they apply to improve generalization and reduce memorization?
⚠ Common exam trap
Google Cloud often tests the misconception that early stopping or batch size adjustments can prevent memorization, when in fact only techniques like differential privacy directly bound the influence of individual training examples.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Apply differential privacy (DP-SGD) during fine-tuning
Differential privacy (DP-SGD) is the correct technique because it directly addresses memorization of sensitive patient data by adding calibrated noise to the gradient updates during fine-tuning. This bounds the model's ability to encode any single individual's information, improving generalization and ensuring compliance with privacy regulations like HIPAA.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Increase the batch size to 64
Why it's wrong here
Larger batch size may slightly regularize but does not prevent memorization of rare data.
- ✗
Increase the number of training epochs
Why it's wrong here
More epochs increase overfitting and memorization.
- ✗
Use early stopping based on validation loss
Why it's wrong here
Early stopping helps generalization but does not provide formal privacy guarantees.
- ✓
Apply differential privacy (DP-SGD) during fine-tuning
Why this is correct
DP-SGD bounds the influence of any single example, reducing memorization and improving privacy.
Go deeper
Related to this question
About these practice questions
One of 683 original Generative AI Leader practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This Generative AI Leader practice question is part of Courseiva's free Google Cloud certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the Generative AI Leader exam.