AI-900 Practice Test 9 — 10 Questions

Question 1

A company uses Azure OpenAI Service to automatically generate customer support email responses. They want to ensure that the model does not produce responses containing offensive language, hate speech, or biased content. Which Microsoft responsible AI principle is most directly addressed by implementing content filters that screen the model's output before it is sent?

Accepted Answer

D. Fairness. Implementing content filters to screen model outputs for offensive language, hate speech, or biased content directly addresses the Fairness principle, which requires AI systems to treat all people equitably and avoid reinforcing societal biases. By filtering out harmful or biased content, the organization ensures that the generated responses do not discriminate against or marginalize any group, aligning with Microsoft's commitment to fairness in AI.

Answer

A. Transparency

Answer

B. Reliability and Safety

Answer

C. Inclusiveness

Question 2

A company needs to extract text from scanned invoices and receipts. Which Azure services are suitable for this task? (Select all that apply.)

Accepted Answer

Computer Vision. Computer Vision (A) is correct because its OCR (Optical Character Recognition) capability can extract printed and handwritten text from images, including scanned invoices and receipts. Form Recognizer (B) is correct because it is specifically designed to extract text, key-value pairs, and tables from forms and documents like invoices and receipts, using prebuilt models. Both services can handle the task, but Form Recognizer is more specialized for structured document extraction.

Answer

Text Analytics

Answer

Custom Vision

Question 3

A company uses a GPT-based model to generate marketing copy. They notice the model occasionally produces text that includes harmful stereotypes. They want to reduce these harmful outputs without retraining the model. Which approach is most appropriate?

Accepted Answer

Prompt engineering with specific instructions to avoid stereotypes. Option B is correct because prompt engineering allows you to guide the model's behavior at inference time without modifying its weights. By including explicit instructions in the prompt (e.g., 'Avoid harmful stereotypes'), you can steer the output toward safer content. This is the most appropriate approach when retraining is not an option, as it directly addresses the undesired outputs through input design.

Answer

Fine-tuning the model on a curated dataset

Answer

Reducing the temperature parameter to zero

Answer

Increasing the maximum output length

Question 4

A retail company wants to automatically determine whether customer reviews are positive, negative, or neutral. Which prebuilt Azure AI Language feature should they use?

Accepted Answer

Sentiment analysis. Sentiment analysis is the correct Azure AI Language feature because it is specifically designed to classify text into positive, negative, or neutral sentiment categories. This prebuilt capability analyzes customer reviews at the document and sentence level, returning a sentiment label and confidence scores, which directly meets the requirement of automatically determining review polarity.

Answer

Key phrase extraction

Answer

Language detection

Answer

Entity recognition

Question 5

A company uses a generative AI model to create blog posts. They want to ensure that the model's output never contains offensive or harmful language before the content is published. They implement a system that checks the generated text against a list of prohibited terms and blocks or edits the content if necessary. Which type of safety measure is this?

Accepted Answer

Post-processing content filtering. Option C is correct because the described system operates after the model generates text, scanning the output against a prohibited terms list and blocking or editing it. This is a classic post-processing content filtering approach, distinct from modifying the model's training data, prompts, or weights. Azure AI Content Safety is an example of such a post-processing filter that can be applied to generative AI outputs.

Answer

Pre-training data cleaning

Answer

Prompt engineering with safety instructions

Answer

Model fine-tuning on safe examples

Question 6

A data scientist is training a binary classification model to detect fraudulent transactions. The dataset contains only 1% fraudulent transactions. The model achieves 99% accuracy on the test set, but when deployed, it fails to detect most actual fraud cases. Which metric would best reveal this issue?

Accepted Answer

Recall. Recall (sensitivity) measures the proportion of actual positive cases correctly identified. In this highly imbalanced dataset (1% fraud), a model can achieve 99% accuracy by simply predicting 'non-fraud' for every transaction, which yields zero true positives. Recall reveals this failure because it focuses solely on how many fraudulent transactions were caught, ignoring the vast majority of non-fraud cases.

Answer

Accuracy

Answer

Precision

Answer

F1 score

Question 7

A data scientist has trained a binary classification model to detect fraudulent credit card transactions. The dataset contains 99.9% legitimate transactions and only 0.1% fraudulent ones. The model predicts all transactions as legitimate, achieving 99.9% accuracy on the test set. However, the business requires the model to actually catch as many fraudulent transactions as possible. Which metric would best reveal the model's failure to identify fraud?

Accepted Answer

Recall. Recall (also known as sensitivity) measures the proportion of actual positive cases (fraudulent transactions) that were correctly identified by the model. In this scenario, the model predicts all transactions as legitimate, so it correctly identifies 0 out of the 0.1% fraudulent transactions, yielding a recall of 0%. This directly reveals the model's complete failure to catch fraud, despite the high accuracy.

Answer

Accuracy

Answer

Precision

Answer

F1 score

Question 8

A hospital uses an AI system to analyze patient records and provide treatment recommendations. They want to ensure that individual patients cannot be re-identified from the data used to train the model. Which Microsoft responsible AI principle is most directly relevant to this requirement?

Accepted Answer

Privacy and security. The requirement to prevent re-identification of individual patients from training data directly aligns with the Privacy and Security principle. This principle mandates that data be anonymized or de-identified to protect personal information, ensuring that individuals cannot be traced back from the dataset. In AI systems, this involves techniques like differential privacy, which adds noise to data to obscure individual contributions while preserving overall statistical patterns.

Answer

Fairness

Answer

Inclusiveness

Answer

Accountability

Question 9

A company builds an AI system to filter job applications and rank candidates. The system is trained on historical hiring data. To reduce potential bias, the company removes protected attributes such as gender and ethnicity from the training data. However, after deployment, the system still shows a statistically significant bias against female candidates. Which Microsoft responsible AI principle most directly requires the company to investigate and address this remaining bias, even when protected attributes are removed?

Accepted Answer

Fairness. The Fairness principle requires AI systems to treat all people fairly and avoid creating or reinforcing discriminatory outcomes. Even when protected attributes like gender are removed from training data, bias can persist through proxy variables (e.g., zip code, education history) that correlate with protected attributes. The company must investigate and mitigate this remaining bias because Fairness mandates proactive assessment and correction of disparate impact, not just removal of obvious features.

Answer

Inclusiveness

Answer

Reliability and safety

Answer

Transparency

Question 10

A data scientist is training a model to classify customer reviews as positive, negative, or neutral. The dataset contains 10,000 reviews, but only 500 of them are negative. The data scientist wants to ensure the model performs well on the minority class (negative reviews). Which technique should the data scientist consider to address the class imbalance?

Accepted Answer

Use a resampling technique like SMOTE or random oversampling of the minority class. Option C is correct because resampling techniques like SMOTE (Synthetic Minority Oversampling Technique) or random oversampling directly address class imbalance by generating synthetic samples or duplicating existing samples from the minority class (negative reviews). This balances the training dataset, preventing the model from being biased toward the majority class (positive/neutral reviews) and improving recall for the minority class.

Answer

Increase the learning rate

Answer

Add more features to the model

Answer

Use L1 regularization (Lasso)