NCA-GENL Core Machine Learning and AI Knowledge Practice Question
A machine learning engineer is fine-tuning a pre-trained language model on a small domain-specific dataset. She notices that the model quickly achieves high accuracy on the training set but performs poorly on the validation set. She wants to mitigate this overfitting without collecting more data. Which technique is most appropriate?
⚠ Common exam trap
The trap here is thinking that more training or a larger batch size can fix overfitting, when they often exacerbate it; regularization techniques like L2 are needed.
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 L2 regularization
L2 regularization is a classic method to combat overfitting by penalizing large weights, which encourages the model to learn simpler patterns that generalize better. When fine-tuning on a small dataset, it is particularly effective because it constrains the model's capacity to memorize noise, improving validation performance.
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 learning rate
Why it's wrong here
Increasing the learning rate would likely cause the model to converge faster to a suboptimal solution or even diverge, worsening overfitting. It does not address the core issue of the model memorizing the training data. In this scenario, a higher learning rate could destabilize fine-tuning and reduce generalization further.
- ✓
Apply L2 regularization
Why this is correct
L2 regularization adds a penalty term to the loss function proportional to the square of the weights, discouraging large weights and reducing overfitting. In fine-tuning on a small dataset, it helps the model generalize better by preventing it from fitting noise. This is a standard and effective technique when additional data is unavailable.
- ✗
Train for more epochs
Why it's wrong here
Training for more epochs would likely worsen overfitting, as the model would continue to memorize the training data and perform even worse on validation. It does not introduce any regularization. In this scenario, early stopping would be more appropriate than extending training.
- ✗
Use a larger batch size
Why it's wrong here
A larger batch size can provide more stable gradients but does not inherently prevent overfitting. In fact, it might allow the model to memorize the training data more efficiently if not paired with other regularization. In this scenario, it would not directly mitigate the overfitting problem.
About these practice questions
Courseiva writes every NCA-GENL question from scratch — 367 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or dumps. Learn why practice questions differ from exam dumps →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official NVIDIA exam blueprint
This NCA-GENL practice question is part of Courseiva's free NVIDIA 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 NCA-GENL exam.