Generative AI Leader Fundamentals of Generative AI Practice Question
A media company is using a generative AI model to produce news summaries. They notice that the summaries sometimes include fabricated details not present in the source articles. Which approach should they take to reduce these hallucinations?
⚠ Common exam trap
The trap here is thinking that a larger model or fine-tuning automatically fixes hallucinations, when grounding with retrieved data is the targeted solution.
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
✓
Ground the model with retrieval-augmented generation (RAG)
Retrieval-augmented generation (RAG) retrieves relevant information from a trusted source and feeds it to the model, ensuring summaries are based on actual content. This reduces hallucinations by anchoring the model's output to provided facts. Other methods like increasing temperature or fine-tuning do not directly address the need for factual grounding.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Increase the model's temperature parameter
Why it's wrong here
Increasing temperature makes the model's output more random and creative, which would likely worsen hallucinations by encouraging it to generate even more speculative content. For factual tasks like news summaries, higher temperature is counterproductive. The goal is to reduce fabrication, so this setting would move in the opposite direction.
- ✗
Fine-tune the model on the company's news articles
Why it's wrong here
Fine-tuning can adapt a model's style or domain knowledge, but it does not provide real-time grounding to specific source articles. The model might still hallucinate details because it is not explicitly given the source text to summarize. Fine-tuning is better for teaching format or tone, not for ensuring factual accuracy against a given document.
- ✓
Ground the model with retrieval-augmented generation (RAG)
Why this is correct
RAG grounds the model by retrieving relevant passages from a trusted knowledge base and providing them as context, so the model generates summaries based on actual source content rather than relying solely on its internal knowledge. This significantly reduces hallucinations because the model is constrained to use the retrieved facts. It is the recommended approach for factual tasks like news summarization.
- ✗
Use a larger model with more parameters
Why it's wrong here
While larger models can sometimes be more accurate, they are not guaranteed to eliminate hallucinations and may still invent details. Simply scaling up the model does not address the root cause of fabricating information not in the source. It could also increase cost and latency without solving the problem, making it an unreliable fix.
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.