AI-900 Practice Question: Describe features of generative AI workloads on Azure
A company uses Azure OpenAI Service to generate summaries of long technical documents. They notice that the model sometimes produces summaries that sound plausible but contain factual errors contradicting the source document. Which concept describes this type of error in large language models?
⚠ Common exam trap
A common mix-up: candidates confuse hallucination with bias or overfitting, not realizing that hallucination specifically describes the generation of confident but false information, while bias relates to systematic prejudice and overfitting to memorization of training data.
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
✓
Hallucination
Hallucination in large language models refers to the generation of content that is factually incorrect or nonsensical but presented with confidence. In this scenario, the model produces summaries that sound plausible yet contain factual errors contradicting the source document, which is the hallmark of hallucination. This occurs because the model generates text based on probabilistic patterns rather than verifying facts against the input.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Overfitting
Why it's wrong here
Overfitting describes a model that has memorized its training data too closely, including irrelevant noise, so it performs poorly on unseen inputs. In generative AI, overfitting might produce outputs that are too similar to specific training examples, but it does not explain the generation of confident falsehoods on novel topics. Hallucination arises from the model's probabilistic text generation, not from over-memorization of training data.
- ✓
Hallucination
Why this is correct
Hallucination in Azure OpenAI's large language models refers to the generation of text that is grammatically correct and plausible-sounding but factually incorrect or fabricated. Because these models predict tokens based on statistical patterns rather than retrieving verified facts, they can confidently assert claims that have no basis in reality. This is exactly the risk in summarization when the model invents details not present in the source material.
- ✗
Tokenization
Why it's wrong here
Tokenization is the mechanical step of splitting raw text into smaller units, such as subwords or tokens, that the model can process. While tokenization affects how the model interprets input and can influence output quality, it does not cause the model to fabricate facts. The falsehoods seen in generative summaries stem from the model's predictive reasoning, not from how the input was segmented.
- ✗
Bias
Why it's wrong here
Bias in AI models refers to systematic and often unfair skews in outputs caused by biased or unrepresentative training data, leading to stereotyped or prejudiced responses. Although biased models can produce inaccurate content, the specific failure mode where a model generates confident but factually wrong information is hallucination. Bias is about distorted patterns, whereas hallucination is about invented content that may or may not align with those patterns.
Go deeper
Related to this question
Learn chapter
Azure Machine Learning Studio
Key term
Model
In IT and AI, a model is a trained mathematical representation that learns patterns from data to make predictions or decisions.
Key term
Service
A service is a software component or system that performs a specific function and is available to be used by other programs or users over a network.
About these practice questions
One of 985 original AI-900 practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. 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.