AI-900 Practice Question: Describe features of generative AI workloads on Azure
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?
⚠ Common exam trap
Many candidates 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.
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
✓
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.
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 adjusts the scale of the softmax distribution before token sampling: higher values (e.g., 1.0+) flatten the distribution so lower-probability tokens become more likely, while lower values sharpen it toward the single most likely token. This changes overall randomness and creativity but applies no per-token frequency or presence penalty, so a token that has already been repeated has no reduced chance of being selected. In fact, excessive temperature can make output more disorganized and, paradoxically, still repetitive.
When this WOULD be correct
A question asks which parameter to increase to make the model generate more creative and less deterministic responses, e.g., 'The model outputs are too predictable and safe. Which parameter should be increased?'
- ✓
Frequency penalty
Why this is correct
The frequency penalty (range -2.0 to 2.0) directly modifies the model's next-token logits: each token's score is decreased in proportion to how many times that token has already appeared in the generated output. By applying this cumulative penalty, Azure OpenAI makes repeated tokens progressively less likely to be selected, actively suppressing verbatim word and phrase repetition. This is the correct control when the goal is to eliminate repetitive marketing copy while preserving coherence.
- ✗
Top-p
Why it's wrong here
Top-p (nucleus sampling) sets a cumulative probability threshold so that only the smallest set of tokens whose total probability meets or exceeds p are eligible for selection. A lower p restricts the candidate list to high-probability tokens, which can make output more focused but, counterintuitively, may increase repetition because it filters out rare, diverse alternatives. It is a diversity-control heuristic, not a repetition penalty that tracks token frequencies.
When this WOULD be correct
A question where the model generates text that is too random or incoherent, and the goal is to make the output more focused and deterministic by narrowing the set of likely tokens. For example: 'The generated text is too creative and goes off-topic. Which parameter should be decreased to make the output more focused?'
- ✗
Max tokens
Why it's wrong here
Max tokens is a generation-length constraint that simply specifies the maximum number of tokens (word pieces) the model may emit before it stops. It is applied after decoding and does not affect the probability distribution of the next token; if the model begins repeating a phrase, max tokens will not intervene before the limit is reached. It limits output size, not output selection behavior, so it cannot address repetition.
When this WOULD be correct
A question asks: 'The marketing team wants to ensure the generated copy does not exceed 150 words. Which parameter should they adjust?' In that case, max tokens would be the correct answer to limit output length.
Option-by-option analysis
Why each answer is right or wrong
Understanding why wrong answers are wrong — and when they would be correct — is what separates a 750 score from a 900. The AI-900 exam frequently reuses these exact scenarios with slightly different constraints.
✓Frequency penaltyCorrect answer▾
Why this is correct
The frequency penalty (range -2.0 to 2.0) directly modifies the model's next-token logits: each token's score is decreased in proportion to how many times that token has already appeared in the generated output. By applying this cumulative penalty, Azure OpenAI makes repeated tokens progressively less likely to be selected, actively suppressing verbatim word and phrase repetition. This is the correct control when the goal is to eliminate repetitive marketing copy while preserving coherence.
✗TemperatureWrong answer — click to see why▾
Why this is wrong here
Temperature controls randomness of token selection, not repetition. Increasing temperature makes output more random but does not directly penalize repeated phrases.
★ When this WOULD be the correct answer
A question asks which parameter to increase to make the model generate more creative and less deterministic responses, e.g., 'The model outputs are too predictable and safe. Which parameter should be increased?'
Why candidates choose this
Candidates may confuse 'repetition' with 'lack of creativity' and assume that increasing randomness (temperature) will reduce repetition, but temperature does not specifically target repeated tokens.
✗Top-pWrong answer — click to see why▾
Why this is wrong here
Top-p controls the cumulative probability threshold for token selection, influencing diversity of word choices, but it does not directly penalize repetition of specific phrases or words. Frequency penalty is the parameter designed to reduce repetition by decreasing the likelihood of tokens that have already appeared.
★ When this WOULD be the correct answer
A question where the model generates text that is too random or incoherent, and the goal is to make the output more focused and deterministic by narrowing the set of likely tokens. For example: 'The generated text is too creative and goes off-topic. Which parameter should be decreased to make the output more focused?'
Why candidates choose this
Candidates may confuse Top-p with frequency penalty because both affect output diversity, but Top-p controls the pool of candidate tokens based on probability mass, not repetition frequency.
✗Max tokensWrong answer — click to see why▾
Why this is wrong here
Max tokens controls the length of the generated text, not the repetition of phrases. Increasing max tokens may allow more text but does not penalize repeated tokens.
★ When this WOULD be the correct answer
A question asks: 'The marketing team wants to ensure the generated copy does not exceed 150 words. Which parameter should they adjust?' In that case, max tokens would be the correct answer to limit output length.
Why candidates choose this
Candidates might think that limiting the output length (max tokens) would reduce repetition by cutting off the generation early, but repetition can occur within any length, and max tokens does not address the underlying cause.
Analysis generated from the official AI-900blueprint and verified against question context. The “when correct” sections are what AI assistants cite when candidates ask “what’s the difference between these options?”
Go deeper
Related to this question
Learn chapter
Azure Machine Learning Studio
Key term
Azure OpenAI Service
Azure OpenAI Service is a cloud platform from Microsoft that lets developers use powerful artificial intelligence models, like GPT-4, to build applications that can understand and generate human-like text, code, images, and more.
Key term
Model
In IT and AI, a model is a trained mathematical representation that learns patterns from data to make predictions or decisions.
About these practice questions
This AI-900 question is part of Courseiva's 985-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam dumps. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
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.