AIF-C01 Applications of Foundation Models Practice Question
An e-commerce company uses Amazon Bedrock to generate product descriptions. They notice the descriptions are too long and contain repetitive phrases. Which parameter adjustment can help?
⚠ Common exam trap
AWS often tests the distinction between frequency penalty and presence penalty, where candidates confuse 'penalizing repetition' with 'reducing randomness' and incorrectly choose temperature or top_p adjustments.
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
✓
Increase frequency penalty
Increasing the frequency penalty reduces the likelihood of the model repeating the same phrases or tokens, directly addressing the issue of repetitive language in generated product descriptions. This parameter penalizes tokens that have already appeared in the text, encouraging more diverse output and naturally shortening overly long descriptions by avoiding redundant loops.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Increase frequency penalty
Why this is correct
Raising the frequency penalty directly penalises tokens proportional to how often they have already appeared, which suppresses the repetitive phrasing the stem describes. It does not shorten output, so pair it with a lower maximum length to address the excessive description length.
- ✗
Increase temperature
Why it's wrong here
Higher temperature increases sampling randomness, which tends to add variation and verbosity rather than shorten text or remove repeated phrases. It is chosen when outputs feel too rigid or identical, not when they are overlong and repetitive.
- ✗
Increase top_p
Why it's wrong here
Top_p controls nucleus sampling, not repetition directly.
- ✗
Decrease presence penalty
Why it's wrong here
Lowering presence penalty rewards tokens already used, actively increasing repetition rather than removing it. Presence penalty is tempting because it is the repetition-control knob, and raising it would be the right adjustment when a model keeps recycling the same phrases across a description.
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.