AIF-C01 Fundamentals of Generative AI Practice Question
A company wants to use a pre-trained generative AI model to analyze customer feedback. They need to adjust the model for their specific domain without retraining from scratch. Which approach is MOST suitable?
⚠ Common exam trap
The AIF-C01 exam often tests the distinction between prompt engineering (a zero-shot or few-shot method that does not modify the model) and fine-tuning (which updates model weights), leading candidates to mistakenly choose prompt engineering as a simpler but insufficient solution for deep domain adaptation.
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
✓
Fine-tuning the model on domain-specific data
Fine-tuning is the most suitable approach because it takes a pre-trained generative AI model and updates its weights using a smaller, domain-specific dataset (e.g., customer feedback transcripts). This allows the model to adapt to the company's specific terminology, sentiment patterns, and context without the massive computational cost and data requirements of training from scratch. It preserves the general language understanding from pre-training while specializing the model for the target domain.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Fine-tuning the model on domain-specific data
Why this is correct
Fine-tuning adapts a pre-trained model's weights using domain-specific customer feedback, satisfying the requirement to specialise without training from scratch. Unlike prompt engineering or RAG, which leave parameters frozen, fine-tuning alters the model itself, embedding domain vocabulary and sentiment patterns directly. This matches the constraint of domain adaptation at lower cost than full retraining.
- ✗
Reinforcement Learning from Human Feedback (RLHF)
Why it's wrong here
RLHF aligns model outputs with human preferences using reward modelling; it does not inject domain vocabulary or task-specific knowledge. It is the right choice when tuning helpfulness, safety or tone; the stem asks for domain adaptation of customer-feedback analysis, which parameter-efficient fine-tuning addresses.
- ✗
Training a new model from scratch on the domain data
Why it's wrong here
Training from scratch discards the pre-trained weights and needs large labelled corpora plus substantial compute, directly contradicting the requirement to avoid retraining from scratch. It is the correct path only when the domain is so unlike existing training data that transfer learning offers no benefit.
- ✗
Using prompt engineering to provide context
Why it's wrong here
Prompt engineering supplies domain context only within the context window, leaving the model's weights unchanged, so terminology and classification behaviour stay generic across sessions. It is the right approach for rapid, low-cost adaptation or prototyping; the stem's requirement to adjust the model for a specific domain implies parameter-efficient fine-tuning.
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 by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
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.