The correct answer is C, increasing the frequency penalty parameter. This works by applying a negative weight to tokens that have already been generated, effectively reducing their probability of being selected again. In Azure OpenAI, the frequency penalty directly targets repetition by scaling down the log-probability of any token based on how often it has already appeared in the output, which forces the model to explore less common words and sentence structures. On the AI-900 exam, this concept tests your understanding of how to control text diversity versus coherence—a common trap is confusing frequency penalty with presence penalty, which penalizes any token that has appeared at least once regardless of frequency. Remember that frequency penalty fights *frequent* repetition, while presence penalty fights *any* repetition. A helpful mnemonic: “Frequency fights the frequent fliers” — the more a word shows up, the harder it is to get picked again.
AI-900 Practice Question: Describe features of generative AI workloads on Azure
This AI-900 practice question tests your understanding of describe features of generative ai workloads on azure. Match the stated requirement to the specific cloud service, access model, or configuration option — many options are valid in isolation but not for this scenario. 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 developer uses Azure OpenAI Service to generate long-form articles. The developer notices that the model tends to repeat the same sentence structures and vocabulary, making the output monotonous. Which parameter should the developer increase to reduce this repetition?
Why wrong: Temperature controls the randomness of token selection; increasing it makes outputs more creative but does not specifically reduce repetition.
B
B
Why wrong: Top_p (nucleus sampling) also controls randomness by limiting token selection to a cumulative probability; it does not directly target repetition.
C
C
Frequency penalty reduces the likelihood of repeating tokens that have already appeared, making the generated text less repetitive.
D
D
Why wrong: Max_tokens sets the maximum number of tokens in the output and does not affect the diversity or repetition of the content.
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
C
Increasing the 'frequency penalty' parameter (option C) reduces repetition by penalizing tokens that have already appeared in the generated text. This encourages the model to use a wider variety of sentence structures and vocabulary, making the output less monotonous.
Key principle: Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
✗
A
Why it's wrong here
Temperature controls the randomness of token selection; increasing it makes outputs more creative but does not specifically reduce repetition.
✗
B
Why it's wrong here
Top_p (nucleus sampling) also controls randomness by limiting token selection to a cumulative probability; it does not directly target repetition.
✓
C
Why this is correct
Frequency penalty reduces the likelihood of repeating tokens that have already appeared, making the generated text less repetitive.
Related concept
Read the scenario before looking for a memorised answer.
✗
D
Why it's wrong here
Max_tokens sets the maximum number of tokens in the output and does not affect the diversity or repetition of the content.
Common exam traps
Common exam trap: answer the scenario, not the keyword
The trap here is confusing the 'frequency penalty' with 'presence penalty' or 'temperature'—candidates often think temperature controls repetition, but it only affects randomness, not the specific suppression of repeated tokens.
Trap categories for this question
Command / output trap
Temperature controls the randomness of token selection; increasing it makes outputs more creative but does not specifically reduce repetition.
Detailed technical explanation
How to think about this question
The frequency penalty applies a logarithmic penalty proportional to the number of times a token has already been generated, directly reducing the likelihood of reusing the same tokens. In contrast, the presence penalty applies a flat penalty regardless of frequency, so it may not sufficiently discourage repeated phrases. In long-form article generation, a higher frequency penalty (e.g., 0.5–1.0) helps maintain lexical diversity without breaking coherence.
KKey Concepts to Remember
Read the scenario before looking for a memorised answer.
Find the constraint that changes the correct option.
Eliminate answers that are true in general but not in this case.
TExam Day Tips
→Watch for words such as best, first, most likely and least administrative effort.
→Review why wrong options are wrong, not only why the correct option is correct.
Key takeaway
Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Real-world example
How this comes up in practice
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.
Related glossary terms
Concepts from this question explained
These glossary pages explain the core terms tested in this AI-900 question in full detail.
Describe features of generative AI workloads on Azure — This question tests Describe features of generative AI workloads on Azure — Read the scenario before looking for a memorised answer..
What is the correct answer to this question?
The correct answer is: C — Increasing the 'frequency penalty' parameter (option C) reduces repetition by penalizing tokens that have already appeared in the generated text. This encourages the model to use a wider variety of sentence structures and vocabulary, making the output less monotonous.
What should I do if I get this AI-900 question wrong?
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
What is the key concept behind this question?
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 →
These questions test the same concept from different angles. Work through them to make sure you can recognise it however the exam phrases it.
Variation 1. A developer uses Azure OpenAI Service to generate product reviews for an e-commerce site. The developer notices that the model often repeats the same phrases within the same review, making the output sound unnatural. Which parameter should the developer adjust to reduce this repetition?
easy
A.Temperature
B.Top_p
C.Max_tokens
✓ D.Frequency_penalty
Why D: The frequency_penalty parameter reduces the likelihood of the model repeating the same phrases by penalizing tokens that have already appeared in the generated text. A higher frequency_penalty value (e.g., 0.5 to 1.0) discourages the model from reusing the same words or phrases, making the output more diverse and natural. This directly addresses the issue of repetitive phrasing in product reviews.
Last reviewed: Jun 11, 2026
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.
This AI-900 practice question is part of Courseiva's free Microsoft 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 AI-900 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.