The answer is catastrophic forgetting, which is the correct cause for the model’s performance drop on the original language understanding task after fine-tuning for summarization. This occurs because fine-tuning a neural network on a new task overwrites the weights that were previously optimized for the original task, causing the model to lose that prior knowledge—a well-known limitation of sequential fine-tuning in deep learning. On the Google Cloud Generative AI Leader exam, this concept tests your understanding of model adaptation risks in Vertex AI, often appearing as a trap where candidates might mistakenly suggest data drift or overfitting instead. The key memory tip is to think of it as “the new task erasing the old one,” like writing new data over a full hard drive without a backup.
Generative AI Leader Fundamentals of Generative AI Practice Question
This Generative AI Leader practice question tests your understanding of fundamentals of generative ai. 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 company fine-tunes a model using Vertex AI and notices the model's performance drops on the original training task (e.g., language understanding) after fine-tuning for a new task (e.g., summarization). What could be the cause?
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Catastrophic forgetting
Catastrophic forgetting occurs when a neural network loses previously learned knowledge upon being fine-tuned on a new task. In this scenario, fine-tuning the model for summarization overwrites the weights responsible for language understanding, causing performance degradation on the original task. This is a well-known limitation of sequential fine-tuning in deep learning.
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.
✗
Data leakage
Why it's wrong here
Data leakage might cause overoptimistic evaluation, not a distinct performance drop on the original task.
✗
Model quantization
Why it's wrong here
Quantization reduces model size but typically does not cause forgetting of original tasks.
✓
Catastrophic forgetting
Why this is correct
Fine-tuning on a narrow task can overwrite general knowledge, leading to performance degradation on the original task.
Related concept
Read the scenario before looking for a memorised answer.
✗
Underfitting
Why it's wrong here
Underfitting would show poor performance on both tasks, not a drop on the original task alone.
Common exam traps
Common exam trap: answer the scenario, not the keyword
Google Cloud often tests the distinction between catastrophic forgetting and underfitting, as candidates may mistakenly think the model simply didn't learn the new task well, rather than recognizing that it forgot the original task due to weight overwriting.
Trap categories for this question
Command / output trap
Underfitting would show poor performance on both tasks, not a drop on the original task alone.
Detailed technical explanation
How to think about this question
Catastrophic forgetting is rooted in the stability-plasticity dilemma: during fine-tuning, gradient updates for the new task shift the model's parameters away from the local minima that encoded the original task. Techniques like elastic weight consolidation (EWC) or replay buffers are used to mitigate this by penalizing changes to important weights. In Vertex AI, this can be observed when fine-tuning a BERT-based model for summarization, where the attention patterns for language understanding are overwritten.
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 healthcare organisation deploys an application with a public-facing web tier and a private database tier. The database subnet has no public IP and only accepts connections from the web tier's security group. Questions like this test whether you can design cloud network isolation using VNets/VPCs, subnets, and security group rules.
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.
What does this Generative AI Leader question test?
Fundamentals of Generative AI — This question tests Fundamentals of Generative AI — Read the scenario before looking for a memorised answer..
What is the correct answer to this question?
The correct answer is: Catastrophic forgetting — Catastrophic forgetting occurs when a neural network loses previously learned knowledge upon being fine-tuned on a new task. In this scenario, fine-tuning the model for summarization overwrites the weights responsible for language understanding, causing performance degradation on the original task. This is a well-known limitation of sequential fine-tuning in deep learning.
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 →
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.
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.