Quick Answer
The answer is Parameter-Efficient Fine-Tuning (PEFT) like LoRA. This approach is correct because it updates only a small subset of parameters—such as low-rank matrices injected into transformer layers—while keeping the vast majority of the foundation model frozen, which dramatically reduces memory and compute costs compared to full fine-tuning. On the Google Cloud Generative AI Leader exam, this question tests your understanding of cost-performance trade-offs when customizing models from Vertex AI Model Garden; a common trap is choosing full fine-tuning for better accuracy, but PEFT delivers comparable results at a fraction of the cost. For a memory tip, remember that PEFT stands for “Partial Efficiency, Full Effectiveness”—you only tweak a tiny fraction of parameters, yet retain the model’s core knowledge, making it the ideal choice for budget-conscious fine-tuning on custom datasets.
This Generative AI Leader practice question tests your understanding of google cloud's generative ai offerings. Read the scenario carefully and evaluate each option against the stated constraints before committing to an answer. After answering, compare your reasoning against the explanation and wrong-answer breakdown below. Once you have made your selection, read the full explanation to reinforce the concept and understand why each distractor is designed to mislead on exam day.
A data scientist wants to fine-tune a foundation model from Vertex AI Model Garden on their custom dataset. They want to choose a cost-effective method that updates only a small subset of parameters. Which fine-tuning approach should they use?
Full fine-tuning
Why wrong: Full fine-tuning updates all parameters and is expensive.
Prompt tuning
Why wrong: Prompt tuning adds soft prompts but doesn't update model weights.
Parameter-Efficient Fine-Tuning (PEFT) like LoRA
PEFT methods update only a small subset of parameters.
Reinforcement Learning from Human Feedback (RLHF)
Why wrong: RLHF aligns models, not a cost-efficient fine-tuning method.
Answer choices
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
Parameter-Efficient Fine-Tuning (PEFT) like LoRA
Option C is correct because Parameter-Efficient Fine-Tuning (PEFT) methods like LoRA (Low-Rank Adaptation) are specifically designed to update only a small subset of parameters (e.g., low-rank matrices injected into transformer layers) while keeping the majority of the foundation model frozen. This drastically reduces memory and compute costs compared to full fine-tuning, making it the most cost-effective choice for customizing a model from Vertex AI Model Garden on a custom dataset.
Key principle: Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Answer analysis
For each option: why learners choose it and why it is or isn't the right answer here.
Full fine-tuning
Why it's wrong here
Full fine-tuning updates all parameters and is expensive.
Prompt tuning
Why it's wrong here
Prompt tuning adds soft prompts but doesn't update model weights.
Parameter-Efficient Fine-Tuning (PEFT) like LoRA
Why this is correct
PEFT methods update only a small subset of parameters.
Related concept
Read the scenario before looking for a memorised answer.
Reinforcement Learning from Human Feedback (RLHF)
Why it's wrong here
RLHF aligns models, not a cost-efficient fine-tuning method.
Common exam traps
The trap here is that candidates often confuse prompt tuning (which does not update model parameters) with parameter-efficient fine-tuning (which updates a small subset of parameters), leading them to incorrectly select Option B as a cost-effective method for updating parameters.
Detailed technical explanation
LoRA works by decomposing weight updates into low-rank matrices (e.g., using rank r=8 or r=16) applied to attention projection layers, reducing trainable parameters by up to 10,000x while maintaining performance. In Vertex AI Model Garden, PEFT methods like LoRA are natively supported via the `peft` library, allowing data scientists to fine-tune models like PaLM 2 or Gemma on custom datasets with minimal GPU memory (e.g., fine-tuning a 7B parameter model on a single A100 GPU). A real-world scenario is adapting a large language model for a domain-specific task (e.g., legal document summarization) where full fine-tuning would be prohibitively expensive, but LoRA achieves comparable results at a fraction of the cost.
Key takeaway
Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Real-world example
A startup's cloud architect reviews their monthly bill and notices costs are higher than expected for a long-running batch job. Switching from on-demand instances to Reserved Instances — or using Spot/Preemptible VMs — can reduce compute costs by up to 72 %. Questions like this test whether you understand the tradeoffs between commitment, flexibility, and cost across cloud pricing models.
What to study next
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
Google Cloud's Generative AI Offerings — study guide chapter
Learn the concepts, then practise the questions
Google Cloud's Generative AI Offerings practice questions
Targeted practice on this topic area only
All Generative AI Leader questions
500 questions across all exam domains
Google Cloud Generative AI Leader Generative AI Leader study guide
Full concept coverage aligned to exam objectives
Generative AI Leader practice test guide
How to use practice tests most effectively before exam day
Related practice questions
Use these pages to review the topic behind this question. This is how one missed question becomes focused revision.
Practise Generative AI Leader questions linked to Fundamentals of Generative AI.
Practise Generative AI Leader questions linked to Business Strategies for Generative AI Solutions.
Practise Generative AI Leader questions linked to Google Cloud's Generative AI Offerings.
Practise Generative AI Leader questions linked to Techniques to Improve Generative AI Model Output.
Practise Generative AI Leader questions linked to Generative AI Leader fundamentals.
Practise Generative AI Leader questions linked to Generative AI Leader scenario.
Practise Generative AI Leader questions linked to Generative AI Leader troubleshooting.
Practice this exam
Short sessions build daily habit. Longer sessions build exam-day stamina. Try a timed session to simulate real conditions.
FAQ
Google Cloud's Generative AI Offerings — This question tests Google Cloud's Generative AI Offerings — Read the scenario before looking for a memorised answer..
The correct answer is: Parameter-Efficient Fine-Tuning (PEFT) like LoRA — Option C is correct because Parameter-Efficient Fine-Tuning (PEFT) methods like LoRA (Low-Rank Adaptation) are specifically designed to update only a small subset of parameters (e.g., low-rank matrices injected into transformer layers) while keeping the majority of the foundation model frozen. This drastically reduces memory and compute costs compared to full fine-tuning, making it the most cost-effective choice for customizing a model from Vertex AI Model Garden on a custom dataset.
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
Read the scenario before looking for a memorised answer.
About these practice questions
Courseiva creates original exam-style practice questions with explanations and wrong-answer analysis. It does not publish real exam questions, exam dumps, or protected exam content. Learn why practice questions differ from exam dumps →
Keep practising
Last reviewed: Jun 25, 2026
This Generative AI Leader practice question is part of Courseiva's free Google Cloud 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 Generative AI Leader exam.
Question Discussion
Share a tip, memory trick, or ask about the reasoning behind this question. Do not post real exam questions, leaked content, braindumps, or copyrighted exam material. Comments are moderated and may be removed without notice.
Sign in to join the discussion.