The answer is to increase the frequency penalty parameter. This works by directly penalizing tokens that have already appeared in the generated text, making the model less likely to reuse the same phrases or words and thereby reducing repetition in Azure OpenAI outputs. On the Microsoft Azure AI Fundamentals AI-900 exam, this question tests your understanding of how to control text generation diversity through specific parameters, often appearing as a scenario where a marketing team needs less repetitive copy. A common trap is confusing frequency penalty with presence penalty—while both encourage diversity, frequency penalty targets repeated tokens specifically, whereas presence penalty encourages discussing new topics. For a quick memory tip, think of “frequency” as “frequent repeats get fined,” so increasing this value directly fines the model for saying the same thing twice.
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 marketing team uses Azure OpenAI Service to generate marketing copy. They notice the generated text is often repetitive, using the same phrases and words multiple times. Which parameter should they increase to directly reduce this repetition?
Why wrong: Temperature controls the randomness of token selection. Increasing it makes the model more creative but does not specifically penalize repetition.
B
Frequency penalty
Correct. A higher frequency penalty reduces the likelihood of the model repeating the same tokens and phrases, directly addressing repetition.
C
Top-p
Why wrong: Top-p controls the cumulative probability of considered tokens; it influences diversity but is not specifically designed to penalize repetition.
D
Max tokens
Why wrong: Max tokens only sets the maximum length of the output; it does not affect whether the model repeats itself.
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Frequency penalty
Frequency penalty directly reduces repetition by penalizing tokens that have already appeared in the generated text. A higher frequency penalty value (e.g., 0.5 to 1.0) decreases the likelihood of the model reusing the same phrases or words, making the output more diverse and less repetitive.
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.
✗
Temperature
Why it's wrong here
Temperature controls the randomness of token selection. Increasing it makes the model more creative but does not specifically penalize repetition.
✓
Frequency penalty
Why this is correct
Correct. A higher frequency penalty reduces the likelihood of the model repeating the same tokens and phrases, directly addressing repetition.
Related concept
Read the scenario before looking for a memorised answer.
✗
Top-p
Why it's wrong here
Top-p controls the cumulative probability of considered tokens; it influences diversity but is not specifically designed to penalize repetition.
✗
Max tokens
Why it's wrong here
Max tokens only sets the maximum length of the output; it does not affect whether the model repeats itself.
Common exam traps
Common exam trap: answer the scenario, not the keyword
The trap here is that candidates often confuse temperature or Top-p with repetition control, but those parameters affect randomness and diversity of vocabulary, not the direct penalization of repeated tokens that frequency penalty provides.
Trap categories for this question
Command / output trap
Max tokens only sets the maximum length of the output; it does not affect whether the model repeats itself.
Detailed technical explanation
How to think about this question
Under the hood, frequency penalty works by subtracting a value proportional to the token's existing frequency from its logit score before sampling. This means each time a token is generated, its probability decreases for subsequent tokens, directly discouraging repetition. In contrast, presence penalty applies a flat penalty regardless of how many times a token appears, so frequency penalty is more effective for reducing repetitive phrases.
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: Frequency penalty — Frequency penalty directly reduces repetition by penalizing tokens that have already appeared in the generated text. A higher frequency penalty value (e.g., 0.5 to 1.0) decreases the likelihood of the model reusing the same phrases or words, making the output more diverse and less repetitive.
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 →
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.