AIF-C01 Applications of Foundation Models Practice Question
A media company uses Amazon Bedrock to generate personalized news summaries. They notice that summaries sometimes include details not present in the source articles. They want to reduce these hallucinations without retraining the model. Which approach should they use?
⚠ Common exam trap
The trap here is assuming that a larger or more capable model will automatically stop hallucinating, when grounding the prompt with retrieved source content is what actually constrains the output.
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
✓
Use Retrieval Augmented Generation (RAG) by retrieving relevant passages from the source articles and including them in the prompt.
Retrieval Augmented Generation supplies the model with relevant excerpts from the source articles at inference time, so the generated summary is conditioned on actual content rather than the model's internal knowledge. This reduces fabricated details without retraining. Other options either increase randomness, rely on model size, or truncate output, none of which ground the response in the provided material.
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 maximum token length in the InvokeModel request.
Why it's wrong here
Limiting output length truncates responses but does not improve factual grounding. The model could still hallucinate within a shorter summary. This parameter controls response size, not correctness, and may cut off important information. It fails to address the underlying issue of the model not being anchored to the source articles.
- ✗
Switch to a larger foundation model with more parameters.
Why it's wrong here
A larger model may have greater general knowledge but does not inherently prevent hallucination when summarizing specific source articles. Without grounding, the model can still fabricate details. Model size does not ensure fidelity to provided documents, and switching models may increase cost and latency without addressing the root cause of ungrounded generation.
- ✓
Use Retrieval Augmented Generation (RAG) by retrieving relevant passages from the source articles and including them in the prompt.
Why this is correct
RAG grounds the model's response by supplying relevant, authoritative content from the source articles directly in the prompt. This reduces hallucination because the model conditions its output on the retrieved text rather than relying solely on parametric knowledge. It requires no retraining and integrates with Amazon Bedrock Knowledge Bases or custom retrieval, making it suitable for dynamic news content.
- ✗
Increase the model's temperature setting to encourage more creative outputs.
Why it's wrong here
Raising temperature increases randomness and diversity in generated text, which would likely worsen hallucinations by making the model more prone to inventing details. The goal is to ground the model in the provided source, so higher temperature is counterproductive. This setting controls sampling randomness, not factual accuracy, and does not leverage the source articles to constrain output.
Go deeper
Related to this question
About these practice questions
Courseiva writes every AIF-C01 question from scratch — 862 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 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.