Generative AI Leader Fundamentals of Generative AI Practice Question
A media company is using a generative AI model to create summaries of news articles. They notice that the summaries sometimes include information not present in the original articles, leading to factual errors. They want to reduce the likelihood of such hallucinations. Which approach should they take?
⚠ Common exam trap
The trap here is assuming that adjusting model parameters like temperature or top-k can eliminate hallucinations, when grounding with source context is the effective method.
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
✓
Provide the article text as context in the prompt and instruct the model to only use that information.
Hallucinations occur when a model generates plausible but unsupported information. To mitigate, you can ground the model by providing the source text in the prompt and instructing it to rely solely on that text. This constrains the model's output to the given context, reducing the chance of introducing external or fabricated details. This is a standard technique in generative AI for summarization.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Decrease the top-k parameter to limit the vocabulary used in the summary.
Why it's wrong here
Top-k limits the number of highest-probability words considered at each step, which can make output more focused but does not prevent the model from introducing facts not in the source. It might reduce creativity but not specifically hallucinations. The core issue is lack of grounding, which top-k does not address.
- ✗
Increase the temperature parameter to encourage more creative outputs.
Why it's wrong here
Increasing the temperature makes the model's output more random and creative, which would likely increase hallucinations rather than reduce them. Higher temperature leads to more diverse but less accurate responses. The goal is to minimize fabricated information, so this is counterproductive.
- ✗
Use a smaller model with fewer parameters to limit the amount of information it can generate.
Why it's wrong here
A smaller model may have less capacity but does not inherently reduce hallucinations. In fact, smaller models might have less knowledge and could still hallucinate. The size of the model is not the primary factor for grounding responses in source material; the approach to conditioning the model is more important.
- ✓
Provide the article text as context in the prompt and instruct the model to only use that information.
Why this is correct
By including the article text in the prompt and explicitly instructing the model to base its summary only on that content, you ground the model's response in the provided source. This technique, often called grounding or context conditioning, significantly reduces hallucinations because the model is constrained to the given text. It is a best practice for summarization tasks.
Go deeper
Related to this question
About these practice questions
Courseiva writes every Generative AI Leader question from scratch — 1,008 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or dumps. Learn why practice questions differ from exam dumps →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official Google Cloud exam blueprint
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.