NCA-GENL Core Machine Learning and AI Knowledge Practice Question
A data scientist is fine-tuning a pretrained large language model on a small domain-specific dataset. The model achieves high accuracy on the training set but poor performance on a held-out validation set. Which technique is most likely to improve the model's generalization?
⚠ Common exam trap
Many candidates confuse overfitting with underfitting, leading to choices that increase model capacity or training time instead of applying regularization.
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 regularization techniques such as dropout or weight decay.
The described symptoms—high training accuracy but poor validation accuracy—are classic signs of overfitting. Regularization techniques such as dropout, weight decay, or early stopping are designed to reduce overfitting by penalizing complexity or adding noise during training. Among the options, applying regularization directly targets the cause, whereas the others either exacerbate overfitting or do not address generalization.
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 number of training epochs to further reduce training loss.
Why it's wrong here
Training for more epochs on a small dataset will likely cause the model to memorize training examples even more, widening the gap between training and validation performance. The scenario already shows overfitting, so additional epochs would worsen generalization. The goal is to improve validation accuracy, not to drive training loss lower. Therefore, this option is counterproductive.
- ✗
Reduce the size of the validation set to decrease evaluation variance.
Why it's wrong here
Shrinking the validation set would make performance estimates noisier and less reliable, not improve the model's generalization. The problem is the model's inability to generalize, not the size of the validation set. A smaller validation set could also lead to misleading conclusions. Thus, this option does not address the overfitting issue.
- ✓
Apply regularization techniques such as dropout or weight decay.
Why this is correct
Regularization methods like dropout and weight decay constrain the model's capacity to memorize training data, encouraging it to learn more generalizable patterns. In this scenario, the large gap between training and validation performance indicates overfitting, so adding regularization is a direct and effective remedy. These techniques are standard in fine-tuning and can be applied without altering the underlying architecture.
- ✗
Increase the learning rate to speed up convergence on the training set.
Why it's wrong here
A higher learning rate might cause the model to converge faster on training data, but it can also lead to unstable training and worse generalization. In an overfitting scenario, accelerating training does not fix the underlying issue of memorization. The model already fits the training set well; the challenge is to improve validation performance, which requires regularization or more data, not a larger learning rate.
About these practice questions
One of 367 original NCA-GENL 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 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.