Quick Answer
The correct answer is to perform RLHF (Reinforcement Learning from Human Feedback) to align the model’s outputs. This technique directly mitigates bias because it uses human evaluators to score model responses, training a reward model that penalizes skewed predictions—such as the over-prediction of positive sentiment—and then fine-tunes the foundation model to optimize for those human-aligned rewards. On the AWS Certified AI Practitioner AIF-C01 exam, this question tests your understanding of how RLHF differs from simpler methods like data rebalancing or prompt engineering; a common trap is assuming bias is only a data issue, when in fact it can stem from misaligned reward signals during fine-tuning. Remember that RLHF doesn’t just reweight data—it reshapes the model’s objective function based on human judgment. A helpful memory tip: think of RLHF as “human-guided course correction” for the model’s behavior, ensuring it learns what people actually value rather than just statistical patterns.
This AIF-C01 practice question tests your understanding of applications of foundation models. Read the scenario carefully and evaluate each option against the stated constraints before committing to an answer. After answering, compare your reasoning against the explanation and wrong-answer breakdown below. Once you have made your selection, read the full explanation to reinforce the concept and understand why each distractor is designed to mislead on exam day.
A company fine-tunes a foundation model on SageMaker JumpStart for sentiment analysis. After deployment, the model shows bias toward positive sentiment. Which action should be taken to mitigate bias?
Use a different foundation model
Why wrong: A different model may still have biases; RLHF is targeted.
Add more positive examples to training data
Why wrong: This may increase bias toward positive sentiment.
Increase training epochs
Why wrong: More epochs can lead to overfitting and reinforce bias.
Perform RLHF (Reinforcement Learning from Human Feedback) to align outputs
RLHF uses human feedback to reduce undesirable biases.
Answer choices
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
Perform RLHF (Reinforcement Learning from Human Feedback) to align outputs
RLHF (Reinforcement Learning from Human Feedback) is the correct approach because it directly addresses the misalignment between the model's outputs and desired human values. By collecting human feedback on model outputs and using it to train a reward model, RLHF fine-tunes the foundation model to reduce biased behavior, such as the over-prediction of positive sentiment, without simply reweighting the training data.
Key principle: Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Answer analysis
For each option: why learners choose it and why it is or isn't the right answer here.
Use a different foundation model
Why it's wrong here
A different model may still have biases; RLHF is targeted.
Add more positive examples to training data
Why it's wrong here
This may increase bias toward positive sentiment.
Increase training epochs
Why it's wrong here
More epochs can lead to overfitting and reinforce bias.
Perform RLHF (Reinforcement Learning from Human Feedback) to align outputs
Why this is correct
RLHF uses human feedback to reduce undesirable biases.
Related concept
Read the scenario before looking for a memorised answer.
Common exam traps
AWS often tests the misconception that bias is solely a data quantity issue, leading candidates to incorrectly choose adding more examples (Option B) instead of recognizing that alignment techniques like RLHF are required to correct model behavior after training.
Detailed technical explanation
RLHF works by first collecting human preference comparisons between model outputs, then training a reward model to predict those preferences, and finally using Proximal Policy Optimization (PPO) to fine-tune the foundation model to maximize the reward. This process directly optimizes for alignment with human values, which is critical for mitigating subtle biases that are not captured by simple data augmentation or model swapping. In real-world scenarios, RLHF has been used to reduce toxic language and improve helpfulness in large language models like GPT-4.
Key takeaway
Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Real-world example
A cloud solutions architect for a retail company is evaluating services for a new workload. The correct answer here reflects best practice for the specific scenario described — not a general cloud recommendation. Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option. Cloud exam questions reward reading the constraint carefully: the same technology can be right or wrong depending on the use case.
What to study next
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
Applications of Foundation Models — study guide chapter
Learn the concepts, then practise the questions
Applications of Foundation Models practice questions
Targeted practice on this topic area only
All AIF-C01 questions
500 questions across all exam domains
AWS Certified AI Practitioner AIF-C01 study guide
Full concept coverage aligned to exam objectives
AIF-C01 practice test guide
How to use practice tests most effectively before exam day
Related practice questions
Use these pages to review the topic behind this question. This is how one missed question becomes focused revision.
Practise AIF-C01 questions linked to Applications of Foundation Models.
Practise AIF-C01 questions linked to Fundamentals of AI and ML.
Practise AIF-C01 questions linked to Fundamentals of Generative AI.
Practise AIF-C01 questions linked to Guidelines for Responsible AI.
Practise AIF-C01 questions linked to Security, Compliance and Governance for AI Solutions.
Practise AIF-C01 questions linked to AIF-C01 fundamentals.
Practise AIF-C01 questions linked to AIF-C01 scenario.
Practise AIF-C01 questions linked to AIF-C01 troubleshooting.
Practice this exam
Short sessions build daily habit. Longer sessions build exam-day stamina. Try a timed session to simulate real conditions.
FAQ
Applications of Foundation Models — This question tests Applications of Foundation Models — Read the scenario before looking for a memorised answer..
The correct answer is: Perform RLHF (Reinforcement Learning from Human Feedback) to align outputs — RLHF (Reinforcement Learning from Human Feedback) is the correct approach because it directly addresses the misalignment between the model's outputs and desired human values. By collecting human feedback on model outputs and using it to train a reward model, RLHF fine-tunes the foundation model to reduce biased behavior, such as the over-prediction of positive sentiment, without simply reweighting the training data.
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
Read the scenario before looking for a memorised answer.
About these practice questions
Courseiva creates original exam-style practice questions with explanations and wrong-answer analysis. It does not publish real exam questions, exam dumps, or protected exam content. Learn why practice questions differ from exam dumps →
Keep practising
Last reviewed: Jun 30, 2026
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.
Question Discussion
Share a tip, memory trick, or ask about the reasoning behind this question. Do not post real exam questions, leaked content, braindumps, or copyrighted exam material. Comments are moderated and may be removed without notice.
Sign in to join the discussion.