AIF-C01 Fundamentals of Generative AI Practice Question
A financial services firm is deploying a generative AI assistant that answers employee questions about internal policy documents. The security team requires that answers be traceable to source text and that the model not invent policy details. Which TWO techniques should be implemented to ground responses and reduce fabricated content? (Choose two.)
⚠ Common exam trap
The trap here is treating a bigger model as a fix for hallucination, when grounding requires supplying evidence and constraining the model to it rather than scaling parameters.
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
✓
Instruct the model to answer only from the supplied context and to state when the context is insufficient
Grounding comes from combining retrieval of authoritative passages with instructions that confine the model to that evidence and permit abstention. Together they make answers traceable and suppress invention. Higher temperature, larger parameter counts, and removal of system instructions either increase variability, fail to supply evidence, or discard the constraints that keep output faithful.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Instruct the model to answer only from the supplied context and to state when the context is insufficient
Why this is correct
Grounding instructions constrain the model to the retrieved material and give it an explicit escape hatch when evidence is missing. That behavior converts a potential hallucination into an honest abstention, which is exactly what the security team wants, and it pairs naturally with retrieval so the model has context to cite.
- ✗
Increase the temperature setting so the model explores a wider range of responses
Why it's wrong here
Higher temperature flattens the probability distribution and increases diversity, which raises the chance of creative or unsupported wording. For a compliance-focused assistant, that is the opposite of the goal. Sampling more broadly does not add factual grounding and can make fabrication more likely, not less.
- ✓
Retrieve relevant passages from the policy corpus and include them in the prompt before generation
Why this is correct
Retrieval-augmented generation supplies the model with authoritative text at inference time, so the answer can be conditioned on real policy language instead of parametric memory. This directly supports traceability because each retrieved passage can be cited, and it reduces fabrication by narrowing what the model must recall on its own.
- ✗
Remove all system instructions so the model can respond more naturally to each question
Why it's wrong here
System instructions are the primary channel for setting boundaries such as cite your sources and do not speculate. Stripping them removes the guardrails that keep responses tethered to policy text, leaving the model free to draw on unrelated training data. This increases risk rather than reducing fabricated content.
- ✗
Expand the model's parameter count by switching to the largest available variant
Why it's wrong here
A larger model may reason better, but scale alone does not guarantee fidelity to internal documents the model never saw during training. Without retrieval or grounding instructions, a bigger model can still produce confident but incorrect policy statements. Model size is not a substitute for supplying evidence.
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.