The answer is frequency penalty. This parameter directly addresses the problem of repetitive phrases by applying a penalty each time a token is generated that has already appeared in the output, effectively reducing the model’s likelihood of reusing the same words or phrases. On the Microsoft Azure AI Fundamentals AI-900 exam, this concept tests your understanding of how to control text diversity in Azure OpenAI models, often appearing in scenarios where you must choose between parameters like temperature, top_p, or frequency penalty to fix repetitive or stale outputs. A common trap is confusing frequency penalty with presence penalty—remember that frequency penalty targets how often a token appears overall, while presence penalty only cares if it has appeared at all. For a quick memory tip, think of “frequency = frequent flier penalty,” where the more a word shows up, the harder it gets to use it 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 to generate product descriptions. The outputs often repeat the same phrases multiple times within a single description. Which parameter should the developer increase to reduce this repetition?
Why wrong: Temperature controls the randomness of the output, increasing it makes the model more creative but does not specifically target repetition.
B
Frequency penalty
Correct. Increasing the frequency penalty discourages the model from repeating the same tokens, reducing repetition.
C
Presence penalty
Why wrong: Presence penalty penalizes any token that has appeared at least once, which encourages the model to talk about new topics but is less effective at reducing repeated phrases than frequency penalty.
D
Max tokens
Why wrong: Max tokens limits the length of the output but does not affect repetition within that length.
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Frequency penalty
The frequency penalty parameter reduces repetition by penalizing tokens that have already appeared in the generated text. Increasing this value discourages the model from reusing the same phrases, 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 the output, increasing it makes the model more creative but does not specifically target repetition.
✓
Frequency penalty
Why this is correct
Correct. Increasing the frequency penalty discourages the model from repeating the same tokens, reducing repetition.
Related concept
Read the scenario before looking for a memorised answer.
✗
Presence penalty
Why it's wrong here
Presence penalty penalizes any token that has appeared at least once, which encourages the model to talk about new topics but is less effective at reducing repeated phrases than frequency penalty.
✗
Max tokens
Why it's wrong here
Max tokens limits the length of the output but does not affect repetition within that length.
Common exam traps
Common exam trap: answer the scenario, not the keyword
The trap here is that candidates confuse frequency penalty with presence penalty, thinking both reduce repetition equally, but frequency penalty specifically targets how often a token appears, while presence penalty only cares if it has appeared at all.
Trap categories for this question
Keyword trap
Presence penalty penalizes any token that has appeared at least once, which encourages the model to talk about new topics but is less effective at reducing repeated phrases than frequency penalty.
Command / output trap
Temperature controls the randomness of the output, increasing it makes the model more creative but does not specifically target repetition.
Detailed technical explanation
How to think about this question
The frequency penalty subtracts a value proportional to the token's cumulative frequency from its logit score before sampling, making repeated tokens less likely to be chosen. In Azure OpenAI, this parameter ranges from -2.0 to 2.0, with positive values reducing repetition. A real-world scenario is generating product descriptions for an e-commerce catalog, where without a frequency penalty, the model might repeatedly say 'high-quality' in every sentence, making the description unnatural.
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 — The frequency penalty parameter reduces repetition by penalizing tokens that have already appeared in the generated text. Increasing this value discourages the model from reusing the same phrases, 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.