NCA-GENL Core Machine Learning and AI Knowledge Practice Question
A machine learning engineer is training a large language model and notices that the model performs exceptionally well on the training data but poorly on a held-out test set. Which technique is most appropriate to mitigate this issue?
⚠ Common exam trap
The trap here is assuming that more training or a larger model will always improve performance, overlooking the need for regularization when overfitting occurs.
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 dropout regularization
Overfitting is characterized by high training performance and poor test performance. Dropout regularization mitigates this by preventing the network from relying on specific neurons, encouraging more robust features. Increasing model size, reducing data, or training longer would all aggravate the problem. Therefore, dropout is the appropriate technique.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Apply dropout regularization
Why this is correct
Dropout randomly deactivates neurons during training, forcing the network to learn redundant representations and preventing co-adaptation. This reduces overfitting and improves generalization to unseen data. In transformer models, dropout is commonly applied to attention weights and feed-forward layers, making it a standard and effective remedy for the described problem.
- ✗
Reduce the size of the training dataset
Why it's wrong here
Reducing training data would likely increase variance and hurt performance further. Overfitting occurs when the model learns noise in the training set; less data would make it harder to learn generalizable patterns. The correct approach is to regularize or augment data, not to shrink it.
- ✗
Train for more epochs
Why it's wrong here
Training for more epochs would allow the model to continue fitting the training data, likely worsening overfitting. The gap between training and test performance would widen. Early stopping is often used to prevent this, but additional epochs are not a solution for overfitting.
- ✗
Increase the model's parameter count
Why it's wrong here
Increasing parameter count would likely worsen overfitting by allowing the model to memorize training data more easily. While larger models can capture more complex patterns, without regularization they exacerbate the gap between training and test performance. The scenario already indicates overfitting, so adding capacity is counterproductive.
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.