- A
Temperature
Why wrong: Temperature scales the logits before the softmax, affecting the overall randomness of sampling. It does not directly limit the pool of tokens based on cumulative probability.
- B
Top_p
Correct. Top_p (nucleus sampling) sets a cumulative probability threshold so that only the most probable tokens that together reach that threshold are considered, eliminating very unlikely tokens.
- C
Frequency penalty
Why wrong: Frequency penalty reduces the tendency to repeat tokens that have already appeared in the generated text. It does not control the probability mass of candidate tokens.
- D
Presence penalty
Why wrong: Presence penalty penalizes tokens that have already been used, encouraging the model to introduce new topics. It does not restrict the token pool based on cumulative probability.
Quick Answer
The answer is Top_p. This parameter controls nucleus sampling, which selects the smallest set of tokens whose combined probability mass reaches the specified threshold—in this case, 0.95—so the model ignores very low-probability tokens that could lead to nonsensical outputs. On the Microsoft Azure AI Fundamentals AI-900 exam, this question tests your understanding of how to fine-tune text generation in Azure OpenAI Service, often contrasting Top_p with Temperature; a common trap is confusing Top_p (which limits the pool of tokens by cumulative probability) with Temperature (which scales the randomness of all token probabilities). Remember the memory tip: “Top_p packs the most probable tokens into a probability pool, cutting off the long tail of unlikely nonsense.”
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. This is a configuration task: choose the command set that satisfies every stated requirement. Small differences — like 'secret' vs 'password' or 'transport input ssh' vs 'all' — change whether the answer is correct. A key principle to apply: top_p (nucleus sampling) sets a cumulative probability threshold for token selection.. 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 product descriptions. They want to ensure that the model only considers the most likely tokens that together have a cumulative probability of 0.95, ignoring very low-probability tokens that could lead to nonsensical outputs. Which parameter should they configure?
Clue words in this question
Noticing these words before you look at the options changes how you read each choice.
Clue:
"most likely"Why it matters: Probability qualifier — the question wants the most probable cause or outcome, not a guaranteed one. Eliminate low-probability options.
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
Top_p
Option B (Top_p) is correct because the developer wants to limit token selection to those with a cumulative probability of 0.95, which is exactly what the Top_p (nucleus sampling) parameter controls. By setting Top_p to 0.95, the model will only consider the smallest set of tokens whose combined probability mass reaches 0.95, effectively ignoring low-probability tokens that could produce nonsensical outputs.
Key principle: Top_p (nucleus sampling) sets a cumulative probability threshold for token selection.
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 scales the logits before the softmax, affecting the overall randomness of sampling. It does not directly limit the pool of tokens based on cumulative probability.
- ✓
Top_p
Why this is correct
Correct. Top_p (nucleus sampling) sets a cumulative probability threshold so that only the most probable tokens that together reach that threshold are considered, eliminating very unlikely tokens.
Clue confirmation
The clue word "most likely" in the question point toward this answer.
Related concept
Top_p (nucleus sampling) sets a cumulative probability threshold for token selection.
- ✗
Frequency penalty
Why it's wrong here
Frequency penalty reduces the tendency to repeat tokens that have already appeared in the generated text. It does not control the probability mass of candidate tokens.
- ✗
Presence penalty
Why it's wrong here
Presence penalty penalizes tokens that have already been used, encouraging the model to introduce new topics. It does not restrict the token pool based on cumulative probability.
Common exam traps
Common exam trap: answer the scenario, not the keyword
The trap here is that candidates often confuse Top_p with Temperature, assuming both control randomness, but Temperature scales logits without filtering low-probability tokens, whereas Top_p directly removes them based on cumulative probability mass.
Detailed technical explanation
How to think about this question
Under the hood, Top_p (nucleus sampling) works by sorting all token probabilities in descending order and then selecting the smallest set of tokens whose cumulative probability exceeds the threshold (e.g., 0.95). This is distinct from Top_k sampling, which selects a fixed number of tokens regardless of their probability distribution. In real-world scenarios, Top_p is often preferred for creative text generation because it dynamically adapts the candidate pool size based on the model's confidence, reducing the risk of generating rare or nonsensical tokens while maintaining diversity.
KKey Concepts to Remember
- Top_p (nucleus sampling) sets a cumulative probability threshold for token selection.
- Tokens are sorted by probability, and only the most probable ones up to the threshold are considered.
- It helps avoid nonsensical outputs by excluding very low-probability tokens.
- A `top_p` value of 0.95 means 95% of the probability mass is considered.
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
Top_p (nucleus sampling) sets a cumulative probability threshold for token selection.
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. Top_p (nucleus sampling) sets a cumulative probability threshold for token selection. Cloud exam questions reward reading the constraint carefully: the same technology can be right or wrong depending on the use case.
What to study next
Got this wrong? Here's your next step.
Review top_p (nucleus sampling) sets a cumulative probability threshold for token selection., then practise related AI-900 questions on the same topic to reinforce the concept.
- →
Describe features of generative AI workloads on Azure — study guide chapter
Learn the concepts, then practise the questions
- →
Describe features of generative AI workloads on Azure practice questions
Targeted practice on this topic area only
- →
All AI-900 questions
1,020 questions across all exam domains
- →
Microsoft Azure AI Fundamentals AI-900 study guide
Full concept coverage aligned to exam objectives
- →
AI-900 practice test guide
How to use practice tests most effectively before exam day
Related practice questions
Related AI-900 practice-question pages
Use these pages to review the topic behind this question. This is how one missed question becomes focused revision.
Describe Artificial Intelligence workloads and considerations practice questions
Practise AI-900 questions linked to Describe Artificial Intelligence workloads and considerations.
Describe fundamental principles of machine learning on Azure practice questions
Practise AI-900 questions linked to Describe fundamental principles of machine learning on Azure.
Describe features of computer vision workloads on Azure practice questions
Practise AI-900 questions linked to Describe features of computer vision workloads on Azure.
Describe features of Natural Language Processing workloads on Azure practice questions
Practise AI-900 questions linked to Describe features of Natural Language Processing workloads on Azure.
Describe features of generative AI workloads on Azure practice questions
Practise AI-900 questions linked to Describe features of generative AI workloads on Azure.
AI-900 fundamentals practice questions
Practise AI-900 questions linked to AI-900 fundamentals.
AI-900 scenario practice questions
Practise AI-900 questions linked to AI-900 scenario.
AI-900 troubleshooting practice questions
Practise AI-900 questions linked to AI-900 troubleshooting.
Practice this exam
Start a free AI-900 practice session
Short sessions build daily habit. Longer sessions build exam-day stamina. Try a timed session to simulate real conditions.
FAQ
Questions learners often ask
What does this AI-900 question test?
Describe features of generative AI workloads on Azure — This question tests Describe features of generative AI workloads on Azure — Top_p (nucleus sampling) sets a cumulative probability threshold for token selection..
What is the correct answer to this question?
The correct answer is: Top_p — Option B (Top_p) is correct because the developer wants to limit token selection to those with a cumulative probability of 0.95, which is exactly what the Top_p (nucleus sampling) parameter controls. By setting Top_p to 0.95, the model will only consider the smallest set of tokens whose combined probability mass reaches 0.95, effectively ignoring low-probability tokens that could produce nonsensical outputs.
What should I do if I get this AI-900 question wrong?
Review top_p (nucleus sampling) sets a cumulative probability threshold for token selection., then practise related AI-900 questions on the same topic to reinforce the concept.
Are there clue words in this question I should notice?
Yes — watch for: "most likely". Probability qualifier — the question wants the most probable cause or outcome, not a guaranteed one. Eliminate low-probability options.
What is the key concept behind this question?
Top_p (nucleus sampling) sets a cumulative probability threshold for token selection.
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 →
Keep practising
More AI-900 practice questions
- A company deploys an AI system to screen job applications. The system is a complex neural network that learns patterns f…
- What is 'model versioning' and why is it essential in MLOps?
- What is 'AI transparency' in Microsoft's Responsible AI principles?
- A company uses Azure OpenAI Service to generate marketing copy. They notice that sometimes the generated text contains r…
- A data scientist is training a regression model to predict house prices using features like square footage, number of be…
- A company uses Azure OpenAI Service to generate marketing copy. They want to ensure that the generated text does not con…
Last reviewed: Jun 11, 2026
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.