- A
When a model generates images instead of text in response to a text prompt
Why wrong: Unexpected output modalities are a model configuration issue — hallucination specifically means generating plausible but factually incorrect text.
- B
When a model generates confident but factually incorrect or fabricated information
Hallucination is confident confabulation — LLMs predict plausible tokens without truth-checking, creating false facts that sound real.
- C
When users imagine the AI is sentient due to very convincing responses
Why wrong: User perception is a human psychology matter — hallucination is a technical term for factually incorrect model outputs.
- D
When a model's training data contains copyrighted material it memorises
Why wrong: Training data memorisation is a copyright/privacy concern — hallucination is about generating false information that was never in any training source.
Quick Answer
The correct answer is that hallucination in large language models occurs when the model generates confident but factually incorrect or fabricated information. This happens because LLMs are fundamentally probabilistic next-token predictors trained on vast, unverified datasets, not databases of grounded facts; they lack any inherent mechanism to distinguish truth from fiction, so they can produce coherent-sounding but entirely false outputs. On the Microsoft Azure AI Fundamentals AI-900 exam, this concept tests your understanding of LLM limitations and the techniques to reduce hallucination, such as retrieval-augmented generation (RAG) with Azure AI Search, careful prompt engineering with system messages, and reinforcement learning from human feedback (RLHF). A common trap is assuming LLMs “know” facts—they don’t; they only predict plausible sequences. Memory tip: think “RAG grounds, prompts bound, RLHF refines” to recall the three key reduction techniques.
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.
What is 'hallucination' in large language models and what techniques help reduce it?
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
When a model generates confident but factually incorrect or fabricated information
Option B is correct because hallucination in large language models (LLMs) refers to the generation of text that is confident, coherent, and plausible-sounding but factually incorrect or entirely fabricated. This occurs because LLMs are probabilistic next-token predictors trained on vast datasets, not databases of verified facts; they lack a built-in mechanism to distinguish truth from fiction. Techniques to reduce hallucination include grounding outputs with retrieval-augmented generation (RAG) using Azure AI Search, prompt engineering with system messages that constrain responses to verified sources, and fine-tuning with human feedback (RLHF) to penalize factual errors.
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.
- ✗
When a model generates images instead of text in response to a text prompt
Why it's wrong here
Unexpected output modalities are a model configuration issue — hallucination specifically means generating plausible but factually incorrect text.
- ✓
When a model generates confident but factually incorrect or fabricated information
Why this is correct
Hallucination is confident confabulation — LLMs predict plausible tokens without truth-checking, creating false facts that sound real.
Related concept
Read the scenario before looking for a memorised answer.
- ✗
When users imagine the AI is sentient due to very convincing responses
Why it's wrong here
User perception is a human psychology matter — hallucination is a technical term for factually incorrect model outputs.
- ✗
When a model's training data contains copyrighted material it memorises
Why it's wrong here
Training data memorisation is a copyright/privacy concern — hallucination is about generating false information that was never in any training source.
Common exam traps
Common exam trap: answer the scenario, not the keyword
The trap here is that candidates confuse hallucination with other common AI issues like modality switching (A), anthropomorphism (C), or data memorization (D), because all involve unexpected or problematic model behavior, but only B captures the core definition of generating confident falsehoods.
Trap categories for this question
Command / output trap
Unexpected output modalities are a model configuration issue — hallucination specifically means generating plausible but factually incorrect text.
Detailed technical explanation
How to think about this question
Under the hood, LLMs like GPT-4 or Llama 2 use transformer architectures with attention mechanisms that assign probabilities to token sequences; hallucination often arises from the model's tendency to 'fill in' gaps with plausible tokens when it lacks relevant training data or when the prompt is ambiguous. A subtle behavior is that hallucination can be amplified by temperature settings above 0.7, which increase randomness, or by insufficient context in the prompt. In a real-world Azure scenario, a customer using Azure OpenAI for medical Q&A without RAG might see the model confidently invent drug interactions, which RAG mitigates by retrieving actual medical literature from Azure Cognitive Search before generating a response.
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.
What to study next
Got this wrong? Here's your next step.
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
- →
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 — Read the scenario before looking for a memorised answer..
What is the correct answer to this question?
The correct answer is: When a model generates confident but factually incorrect or fabricated information — Option B is correct because hallucination in large language models (LLMs) refers to the generation of text that is confident, coherent, and plausible-sounding but factually incorrect or entirely fabricated. This occurs because LLMs are probabilistic next-token predictors trained on vast datasets, not databases of verified facts; they lack a built-in mechanism to distinguish truth from fiction. Techniques to reduce hallucination include grounding outputs with retrieval-augmented generation (RAG) using Azure AI Search, prompt engineering with system messages that constrain responses to verified sources, and fine-tuning with human feedback (RLHF) to penalize factual errors.
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 →
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.