LLM Fundamentals →mediumMultiple ChoiceObjective-mapped

1Z0-1127-25 LLM Fundamentals Practice Question

A company wants to build a sentiment analysis system for customer reviews. They have a labeled dataset of 10,000 reviews. Which approach is most cost-effective and likely to yield good performance?

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

✓

Fine-tune a pre-trained BERT model on the labeled dataset

Fine-tuning a pre-trained encoder-only model like BERT on the labeled dataset is a standard approach for classification tasks, offering good performance with relatively modest data and compute.

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

✗
Use GPT-4 with a prompt and no fine-tuning
Why it's wrong here
Using a large decoder-only model via API can be expensive and may not be as accurate as fine-tuned BERT for classification.
✗
Use a simple bag-of-words model with logistic regression
Why it's wrong here
While simple, this model may not capture complex semantics as well as fine-tuned BERT.
✓
Fine-tune a pre-trained BERT model on the labeled dataset
Why this is correct
BERT is pre-trained for language understanding; fine-tuning on a small classification dataset is efficient and effective.
✗
Train a Transformer model from scratch on the reviews
Why it's wrong here
Training from scratch requires large amounts of data and compute; 10k reviews is insufficient.

Go deeper

1Z0-1127-25 LLM Fundamentals Practice Question

Why each option matters

Option-by-option breakdown

Related to this question