- A
Using prompt engineering with in-context learning
Why wrong: In-context learning works for few-shot tasks but may not provide deep domain adaptation.
- B
Full fine-tuning of all model parameters
Why wrong: Full fine-tuning is computationally expensive and risks overfitting with limited data.
- C
Training a new model from scratch on the domain data
Why wrong: Training from scratch requires enormous data and compute, not feasible for limited data.
- D
Adapter-based fine-tuning using LoRA
LoRA is parameter-efficient, cost-effective, and reduces forgetting.
Question 978 of 997
Generative AI Leader Generative AI Concepts and Technologies Practice Question
This Generative AI Leader practice question tests your understanding of generative ai concepts and technologies. 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 is fine-tuning a large language model for a specialized domain using limited labeled data. To avoid catastrophic forgetting and reduce computational cost, which approach is recommended?
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
✓
Adapter-based fine-tuning using LoRA
Adapter-based fine-tuning using LoRA (Low-Rank Adaptation) is recommended because it freezes the pre-trained model weights and injects trainable low-rank matrices into the transformer layers. This approach drastically reduces the number of parameters to update (often by 10,000x), lowering memory and compute requirements, while preserving the original knowledge to prevent catastrophic forgetting on limited domain data.
Key principle: Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Using prompt engineering with in-context learning
Why it's wrong here
In-context learning works for few-shot tasks but may not provide deep domain adaptation.
- ✗
Full fine-tuning of all model parameters
Why it's wrong here
Full fine-tuning is computationally expensive and risks overfitting with limited data.
- ✗
Training a new model from scratch on the domain data
Why it's wrong here
Training from scratch requires enormous data and compute, not feasible for limited data.
- ✓
Adapter-based fine-tuning using LoRA
Why this is correct
LoRA is parameter-efficient, cost-effective, and reduces forgetting.
Related concept
Read the scenario before looking for a memorised answer.
Common exam traps
Common exam trap: answer the scenario, not the keyword
Cisco often tests the misconception that prompt engineering (Option A) is a form of fine-tuning, when in fact it is a zero-shot or few-shot inference technique that does not modify model parameters, making it unsuitable for persistent domain adaptation with limited labeled data.
Detailed technical explanation
How to think about this question
LoRA works by decomposing the weight update matrix ΔW into two low-rank matrices A and B (e.g., rank r=8), so that the forward pass becomes h = W₀x + BAx, where only A and B are trained. In practice, LoRA can be applied to attention projection matrices (Q, K, V, O) and sometimes to feed-forward layers, enabling fine-tuning with as few as 0.1% of total parameters. A real-world scenario is fine-tuning a 70B-parameter model on medical records with only 1,000 examples, where LoRA reduces GPU memory from ~140GB to ~16GB and completes training in hours instead of days.
KKey Concepts to Remember
- Read the scenario before looking for a memorised answer.
- Find the constraint that changes the correct option.
- Eliminate answers that are true in general but not in this case.
TExam Day Tips
- Watch for words such as best, first, most likely and least administrative effort.
- Review why wrong options are wrong, not only why the correct option is correct.
Key takeaway
Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Real-world example
How this comes up in practice
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
Got this wrong? Here's your next step.
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
- →
Generative AI Concepts and Technologies — study guide chapter
Learn the concepts, then practise the questions
- →
Generative AI Concepts and Technologies practice questions
Targeted practice on this topic area only
- →
All Generative AI Leader questions
997 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
Related Generative AI Leader practice-question pages
Use these pages to review the topic behind this question. This is how one missed question becomes focused revision.
Fundamentals of Generative AI practice questions
Practise Generative AI Leader questions linked to Fundamentals of Generative AI.
Business Strategies for Generative AI Solutions practice questions
Practise Generative AI Leader questions linked to Business Strategies for Generative AI Solutions.
Generative AI Concepts and Technologies practice questions
Practise Generative AI Leader questions linked to Generative AI Concepts and Technologies.
Google AI Ecosystem and Strategy practice questions
Practise Generative AI Leader questions linked to Google AI Ecosystem and Strategy.
Responsible AI and Data Governance practice questions
Practise Generative AI Leader questions linked to Responsible AI and Data Governance.
Google Cloud's Generative AI Offerings practice questions
Practise Generative AI Leader questions linked to Google Cloud's Generative AI Offerings.
Techniques to Improve Generative AI Model Output practice questions
Practise Generative AI Leader questions linked to Techniques to Improve Generative AI Model Output.
Applying Generative AI in Business practice questions
Practise Generative AI Leader questions linked to Applying Generative AI in Business.
Generative AI Leader fundamentals practice questions
Practise Generative AI Leader questions linked to Generative AI Leader fundamentals.
Generative AI Leader scenario practice questions
Practise Generative AI Leader questions linked to Generative AI Leader scenario.
Generative AI Leader troubleshooting practice questions
Practise Generative AI Leader questions linked to Generative AI Leader troubleshooting.
Practice this exam
Start a free Generative AI Leader practice session
Short sessions build daily habit. Longer sessions build exam-day stamina. Try a timed session to simulate real conditions.
FAQ
Questions learners often ask
What does this Generative AI Leader question test?
Generative AI Concepts and Technologies — This question tests Generative AI Concepts and Technologies — Read the scenario before looking for a memorised answer..
What is the correct answer to this question?
The correct answer is: Adapter-based fine-tuning using LoRA — Adapter-based fine-tuning using LoRA (Low-Rank Adaptation) is recommended because it freezes the pre-trained model weights and injects trainable low-rank matrices into the transformer layers. This approach drastically reduces the number of parameters to update (often by 10,000x), lowering memory and compute requirements, while preserving the original knowledge to prevent catastrophic forgetting on limited domain data.
What should I do if I get this Generative AI Leader question wrong?
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
What is the key concept behind this question?
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 →
Last reviewed: Jul 4, 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.