AIF-C01 Fundamentals of Generative AI Practice Question
A media company's generative AI writing assistant produces fluent but sometimes fabricated statistics. The team wants to reduce these hallucinations without changing the foundation model. Which action best addresses the root cause?
⚠ Common exam trap
The trap here is treating sampling parameters as accuracy controls when they only shape randomness and diversity of token selection.
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's responses by supplying verified reference documents in the prompt and instructing it to cite them
Fabricated statistics stem from the model generating text without an authoritative factual anchor. Supplying verified documents and requiring citations ties each claim to a source, which reduces invention while leaving the model untouched. Token limits, parameter count, and sampling parameters influence length, capacity, and randomness respectively, none of which ground output in verified facts.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Raise the top-p sampling value to make token selection more deterministic
Why it's wrong here
Top-p controls the nucleus of tokens considered during sampling. Adjusting it changes diversity and randomness, not the factual basis of the content. A more deterministic sampler can repeat the same fabricated statistic consistently, so it does not resolve the grounding problem.
- ✗
Lower the maximum token limit for each response
Why it's wrong here
Truncating output length does not improve factual accuracy; a short response can still contain invented statistics. The token limit governs how much text is produced, not whether that text is grounded, so this change would shorten answers while leaving the underlying hallucination behavior intact.
- ✗
Switch the model to a smaller parameter count to reduce creativity
Why it's wrong here
Model size correlates loosely with capability, not truthfulness. A smaller model may hallucinate more, not less, because it has less capacity to absorb factual patterns. Parameter count is not the lever that ties output to verified sources, so this choice misdiagnoses the cause.
- ✓
Ground the model's responses by supplying verified reference documents in the prompt and instructing it to cite them
Why this is correct
Hallucinated statistics occur when the model generates plausible-sounding content without a factual anchor. Providing verified source documents in the prompt and requiring citations constrains generation to supported claims, reducing fabrication without modifying model weights, which matches the constraint of not changing the foundation model.
Go deeper
Related to this question
About these practice questions
One of 862 original AIF-C01 practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. 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 Amazon Web Services exam blueprint
This AIF-C01 practice question is part of Courseiva's free Amazon Web Services 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 AIF-C01 exam.