AI-900 Practice Test 38 — 15 Questions

Question 1

What is the maximum output length parameter 'max tokens' used for in Azure OpenAI?

Accepted Answer

The maximum number of tokens in the generated response to control length and cost. The 'max tokens' parameter in Azure OpenAI controls the maximum number of tokens (roughly 0.75 words per token) that the model can generate in a single response. This directly limits the length of the output, which in turn controls both the cost (since Azure OpenAI charges per token) and the response size, preventing excessively long or expensive completions.

Answer

The maximum number of API requests per second

Answer

The maximum number of words in the input prompt

Answer

The maximum number of concurrent users of the model

Question 2

A healthcare start-up proposes a fully automated AI system to diagnose patients from medical scans without any human doctor review. They claim the system is 99% accurate. According to Microsoft's responsible AI principles, which principle is most directly violated by removing human oversight from this critical decision-making process?

Accepted Answer

Accountability. Removing human oversight from a fully automated diagnostic system violates the accountability principle. Microsoft's responsible AI principle of accountability requires that humans remain responsible for AI-driven decisions, especially in high-stakes healthcare scenarios where errors can have life-or-death consequences. By eliminating any human doctor review, the start-up fails to ensure that a human can intervene, validate, or take responsibility for the system's outputs.

Answer

Fairness

Answer

Reliability and safety

Answer

Transparency

Question 3

A marketing agency wants to use Azure OpenAI Service to generate product descriptions that consistently match a client's distinctive brand voice. They have a collection of 50 sample descriptions written in the desired tone and style. Which Azure OpenAI Service capability should they use to specialize the model to produce text that closely matches this style?

Accepted Answer

Fine-tuning. Fine-tuning (C) is the correct choice because it allows the marketing agency to train the Azure OpenAI model on their 50 sample descriptions, adjusting the model's weights to specialize its output to match the client's distinctive brand voice. Unlike prompt engineering or parameter adjustments, fine-tuning creates a custom model that internalizes the style and tone from the provided examples, enabling consistent generation without needing lengthy instructions in every prompt.

Answer

Temperature parameter adjustment

Answer

Prompt engineering with detailed instructions

Answer

Content filtering

Question 4

A legal research company needs to automatically extract specific case citation patterns (e.g., '123 U.S. 456') from thousands of legal documents. The standard named entity recognition in Azure AI Language does not recognize these custom citation formats. Which Azure AI Language feature should they use to create a model that extracts these custom entities?

Accepted Answer

Custom Named Entity Recognition. Custom Named Entity Recognition (NER) is the correct choice because it allows you to train a model to extract domain-specific entities, such as legal citation patterns like '123 U.S. 456', that are not recognized by the pre-built NER in Azure AI Language. Unlike standard NER, which only identifies common entity types (e.g., person, location, date), Custom NER lets you define custom entity labels and train the model with labeled examples to recognize these specific patterns in legal documents.

Answer

Sentiment Analysis

Answer

Key Phrase Extraction

Answer

Conversational Language Understanding

Question 5

What is 'chain-of-thought prompting' and when is it most effective?

Accepted Answer

Prompting the model to show explicit reasoning steps before giving a final answer. Chain-of-thought prompting instructs the model to break down a complex problem into intermediate reasoning steps before producing the final answer. This technique improves accuracy on tasks requiring multi-step logic, such as arithmetic, commonsense reasoning, or symbolic manipulation, by making the model's internal reasoning explicit and reducing errors from shortcut answers.

Answer

Linking multiple AI models in a pipeline where each model's output feeds the next

Answer

Training a model on a sequence of related documents to build contextual knowledge

Answer

A method for connecting chatbot conversation turns to maintain long-term memory

Question 6

What capability does Azure AI Vision's 'celebrity recognition' feature provide?

Accepted Answer

Identifying well-known public figures in images and returning their names with confidence scores. Azure AI Vision's celebrity recognition feature is a specialized domain-specific model that identifies well-known public figures (e.g., actors, politicians, athletes) within images. It returns the recognized celebrity's name along with a confidence score, enabling applications like media indexing or social media analysis. This capability is built on top of the general object detection and facial recognition models, but is pre-trained on a curated dataset of celebrity faces.

Answer

Automatically scheduling meetings with celebrities based on their availability

Answer

Generating fictional celebrity lookalikes for entertainment applications

Answer

Verifying celebrity identities for event access control

Question 7

A photo sharing app wants to automatically generate descriptive captions for uploaded photos to improve accessibility for visually impaired users. Which Azure Computer Vision feature should they use?

Accepted Answer

Describe Image (Image Captioning). The Describe Image (Image Captioning) feature of Azure Computer Vision generates human-readable captions that describe the content of an image. This directly meets the requirement of automatically generating descriptive captions for uploaded photos to improve accessibility for visually impaired users.

Answer

Optical Character Recognition (OCR)

Answer

Object Detection

Answer

Image Classification

Question 8

A data scientist is building a classification model to detect fraudulent transactions. The dataset has 1,000,000 legitimate transactions and only 1,000 fraudulent ones. The model achieves 99.9% accuracy on the test set, but it fails to catch most fraudulent cases. Which metric should the data scientist prioritize to better evaluate the model's performance on this imbalanced dataset?

Accepted Answer

Recall. Recall measures the proportion of actual positive cases (fraudulent transactions) correctly identified by the model. With only 1,000 fraud cases out of 1,001,000 total transactions, a model that predicts 'legitimate' for every transaction would achieve 99.9% accuracy but 0% recall, making recall the critical metric for imbalanced fraud detection.

Answer

Accuracy

Answer

Mean Squared Error

Answer

R-squared

Question 9

What is 'context length' limitation in LLMs and how do 'long-context models' address it?

Accepted Answer

The maximum text an LLM can process at once — long-context models extend this to 128K+ tokens. 'context length' in large language models (LLMs) refers to the maximum number of tokens (words, subwords, or characters) the model can process in a single input, including both the prompt and the generated output. Long-context models, such as GPT-4 Turbo or Claude 3, extend this limit to 128K tokens or more, enabling the model to handle entire documents, lengthy conversations, or large codebases without truncation.

Answer

The physical cable length limitation when connecting AI servers in a data centre

Answer

The minimum number of examples required before the model produces reliable outputs

Answer

The duration (in seconds) before an Azure OpenAI API request times out

Question 10

A retail chain wants to automatically detect which specific products are missing from store shelves by analyzing images from in-store cameras. Each product has a distinct shape and label. Which Azure Computer Vision capability is most appropriate for this task?

Accepted Answer

B) Object Detection. Object Detection (Option B) is the correct choice because it can identify and locate multiple products within an image by drawing bounding boxes around each detected object. This allows the system to determine which specific products are missing by comparing detected items against an expected inventory list. Image Classification would only label the entire image, not individual products, while OCR focuses on text extraction and Facial Recognition identifies people.

Answer

A) Image Classification

Answer

C) Optical Character Recognition (OCR)

Answer

D) Facial Recognition

Question 11

A manufacturing company deploys an AI system to predict equipment failures from sensor data. They need to ensure the system continues to function correctly even if some sensors malfunction or provide noisy data. Which responsible AI principle is most directly relevant?

Accepted Answer

B: Reliability and safety. The scenario describes an AI system that must continue to function correctly despite sensor malfunctions or noisy data. This directly aligns with the reliability and safety principle, which ensures that AI systems operate consistently and safely under varying conditions, including edge cases and unexpected inputs. In predictive maintenance, robustness to sensor noise is critical to avoid false alarms or missed failures.

Answer

A: Fairness

Answer

C: Transparency

Answer

D: Accountability

Question 12

What is 'keyword extraction' vs 'key phrase extraction' in Azure AI Language?

Accepted Answer

Both terms refer to the same Azure AI Language feature that extracts important concept phrases from text. In Azure AI Language, 'key phrase extraction' is the official feature name that identifies the main concepts in a text, and 'keyword extraction' is an informal term sometimes used interchangeably. The service does not distinguish between single-word and multi-word extraction as separate features; it returns a list of key phrases that can be single words or multi-word expressions based on the text's context.

Answer

Keyword extraction returns single words; key phrase extraction returns multi-word phrases

Answer

Keyword extraction is a legacy feature; key phrase extraction is the new replacement

Answer

Key phrase extraction requires custom training; keyword extraction uses pre-built models

Question 13

A data scientist is training a credit risk model and wants to use Azure Machine Learning's Responsible AI dashboard to identify if the model is biased against a certain demographic group. Which component of the dashboard should they use to evaluate this?

Accepted Answer

Model Fairness Assessment. The Model Fairness Assessment component of Azure Machine Learning's Responsible AI dashboard is specifically designed to evaluate and mitigate bias in machine learning models. It allows data scientists to assess disparities in model performance across demographic groups defined by sensitive features (e.g., race, gender) using metrics like demographic parity, equal opportunity, and disparate impact. This directly addresses the question of identifying bias against a certain demographic group.

Answer

Model Interpretability

Answer

Error Analysis

Answer

Data Balance Analysis

Question 14

A logistics company wants to automatically extract the tracking numbers, delivery addresses, and sender names from scanned shipping labels. Which prebuilt Azure Computer Vision capability should they use?

Accepted Answer

Optical Character Recognition (OCR). (Optical Character Recognition, or OCR) is correct because the task requires extracting text (tracking numbers, addresses, sender names) from scanned images. Azure Computer Vision's OCR API is specifically designed to detect and read printed or handwritten text from images, returning the text content along with bounding boxes. Object Detection, Image Classification, and Face Detection do not extract text, making OCR the appropriate prebuilt capability.

Answer

Object Detection

Answer

Image Classification

Answer

Face Detection

Question 15

A legal firm needs to automatically extract specific terms such as contract dates, party names, and monetary amounts from thousands of legal documents. The firm does not have a labeled dataset for custom training but needs to identify only these predefined types of information. Which prebuilt Azure AI Language feature should they use?

Accepted Answer

Named Entity Recognition (NER). Named Entity Recognition (NER) is the correct choice because it is a prebuilt Azure AI Language feature designed to automatically identify and categorize predefined entities such as dates, person names, and monetary amounts from text. Since the firm needs to extract specific types of information (contract dates, party names, monetary amounts) without a labeled dataset, NER's out-of-the-box models can directly recognize these common entity categories without any custom training.

Answer

Key phrase extraction

Answer

Sentiment analysis

Answer

Language detection