Free Preparation Discussions
MENU
NVIDIA NCA-GENL Exam - Topic 3 Question 13 Discussion
Topic #: 3
In the context of evaluating a fine-tuned LLM for a text classification task, which experimental design technique ensures robust performance estimation when dealing with imbalanced datasets?
Stratified k-fold cross-validation is a robust experimental design technique for evaluating machine learning models, especially on imbalanced datasets. It divides the dataset into k folds while preserving the class distribution in each fold, ensuring that the model is evaluated on representative samples of all classes. NVIDIA's NeMo documentation on model evaluation recommends stratified cross-validation for tasks like text classification to obtain reliable performance estimates, particularly when classes are unevenly distributed (e.g., in sentiment analysis with few negative samples). Option A (single hold-out) is less robust, as it may not capture class imbalance. Option C (bootstrapping) introduces variability and is less suitable for imbalanced data. Option D (grid search) is for hyperparameter tuning, not performance estimation.
NVIDIA NeMo Documentation: https://docs.nvidia.com/deeplearning/nemo/user-guide/docs/en/stable/nlp/model_finetuning.html
Silva
3 months agoHolley
3 months agoLaurel
3 months agoTroy
3 months agoDetra
4 months agoElfriede
4 months agoLeila
4 months agoJohnna
5 months agoElise
5 months agoDanica
5 months agoKimbery
5 months agoColton
5 months agoCherilyn
5 months agoGearldine
6 months agoWhitley
6 months agoDacia
6 months agoGlenna
6 months agoJoseph
6 months agoRocco
6 months agoTerrilyn
7 months agoAlease
7 months agoZita
7 months agoBuddy
7 months agoFrederica
7 months agoMalissa
8 months agoEugene
2 months agoChau
2 months agoHuey
2 months agoKris
3 months agoDortha
3 months ago