AI0-001 AI Concepts and Techniques Practice Test 4 — 15 Questions

Question 1

A data scientist is evaluating a binary classification model. The model achieves 95% accuracy on the test set, but the precision is 0.60 and recall is 0.55. The dataset has 90% negative class samples. Which metric should the team focus on to improve the model?

Choose an answer to begin — your selection is scored in the full session.

Accepted Answer

F1 score. With 90% negative class samples, accuracy is misleading because a trivial majority-class classifier would score 90%. The low precision (0.60) and recall (0.55) indicate the model struggles on the minority positive class. The F1 score, being the harmonic mean of precision and recall, is the right metric to optimise because it balances both concerns on imbalanced data.

Answer

Perplexity

Answer

BLEU score

Answer

Accuracy

Question 2

A team is fine-tuning a BERT model for a document classification task. They notice the model achieves high F1 scores on the training set but low F1 on the validation set. Which regularization technique would be MOST effective?

Accepted Answer

Dropout. Dropout is the most effective regularization for transformer-based models like BERT because it randomly deactivates neurons during training, forcing the network to learn redundant representations and preventing co-adaptation. BERT already includes dropout layers in its architecture (attention dropout, hidden dropout), and increasing or tuning the dropout rate directly addresses overfitting on the training set.

Answer

L1 regularization

Answer

L2 regularization

Answer

Reduce batch size

Question 3

In unsupervised learning, which task involves grouping similar data points together based on feature similarities?

Accepted Answer

Clustering. Clustering is the unsupervised learning task that groups similar data points based on feature similarities, without predefined labels. It identifies inherent structures in data by minimizing intra-cluster distances and maximizing inter-cluster distances. Common algorithms include K-means, DBSCAN, and hierarchical clustering. This contrasts with supervised tasks like classification and regression, which require labeled data.

Answer

Anomaly detection

Answer

Classification

Answer

Regression

Question 4

A developer is using a large language model via an API. They want the model to solve a math problem step by step. Which prompt engineering technique should they use?

Accepted Answer

Chain-of-thought prompting. Chain-of-thought (CoT) prompting explicitly instructs the model to reason through intermediate steps before producing a final answer, which is exactly what's needed for multi-step math problems. By asking the model to 'think step by step,' it decomposes the problem into manageable reasoning stages, significantly improving accuracy on arithmetic and logic tasks.

Answer

Set temperature to 0.9

Answer

Few-shot prompting

Answer

Zero-shot prompting

Question 5

A company wants to deploy an LLM-based chatbot that can handle sensitive customer information. Which THREE measures should be implemented to mitigate prompt injection attacks? (Choose 3)

Accepted Answer

Use a system prompt that instructs the model to ignore any instructions in the user input. Option A is correct because a hardened system prompt that explicitly tells the model to treat user input as data and ignore embedded instructions is a primary defense against prompt injection, helping the model distinguish trusted developer instructions from untrusted user content. Option B is correct because output filtering adds a defense-in-depth layer that inspects the model's responses for harmful, leaked, or policy-violating content before it reaches the user, catching injections that bypass input controls. Option C is correct because sanitizing user inputs by stripping or escaping special characters, control tokens, and injection-style delimiters (e.g., markdown fences or role-play markers) reduces the attack surface for crafted prompts. Option D is not correct because model size does not determine resistance to prompt injection; smaller models can still be manipulated and may even be more susceptible. Option E is not correct because temperature controls randomness in token sampling, not the model's adherence to injected instructions, so lowering it does not mitigate prompt injection.

Answer

Use a smaller model with fewer parameters

Answer

Set temperature to a low value

Question 6

A data scientist needs to predict whether a customer will churn (yes/no) based on historical data. Which type of machine learning problem is this?

Accepted Answer

Binary classification. This is a binary classification problem because the target variable has exactly two discrete outcomes: 'yes' (churn) or 'no' (no churn). Classification algorithms such as logistic regression, decision trees, or support vector machines are used to assign input features to one of these two predefined classes. The output is a categorical label, not a continuous value or a reward signal.

Answer

Reinforcement learning

Answer

Regression

Answer

Clustering

Question 7

A team trains a neural network for image classification. During training, the loss decreases on the training set but increases on the validation set after a few epochs. What is the most likely cause?

Accepted Answer

Overfitting. Overfitting occurs when the model learns the training data too well, including noise and irrelevant patterns, causing it to memorize rather than generalize. This is evidenced by the loss decreasing on the training set while increasing on the validation set after a few epochs, as the model's performance on unseen data degrades.

Answer

Vanishing gradients

Answer

Incorrect learning rate scheduling

Answer

Underfitting

Question 8

A generative AI model is asked to 'Write a poem about AI' and returns a very short, generic response. The user wants longer, more creative outputs. Which parameter adjustment is MOST likely to help?

Accepted Answer

Increase the temperature parameter. Increasing the temperature parameter raises the randomness of token selection, encouraging the model to explore less probable word sequences and produce more varied, creative, and longer outputs. A low temperature (e.g., 0.1) makes the model deterministic and repetitive, often yielding short, generic responses. By increasing temperature (e.g., to 0.8 or 1.0), the model is more likely to generate diverse and expansive text, directly addressing the user's request for longer, more creative poems.

Answer

Decrease the top-p value

Answer

Increase the frequency penalty

Answer

Decrease the max tokens limit

Question 9

Which type of neural network is BEST suited for processing sequential data such as time series or natural language?

Accepted Answer

Recurrent Neural Network (RNN). Recurrent Neural Networks (RNNs) maintain a hidden state that carries information across time steps, making them inherently suited to sequential data like time series and natural language. Their recurrent connections allow them to model order and temporal dependencies, which feedforward architectures cannot do natively.

Answer

Generative Adversarial Network (GAN)

Answer

Multi-layer Perceptron (MLP)

Answer

Convolutional Neural Network (CNN)

Question 10

An AI engineer is tuning a large language model for a summarization task. The output summaries are too verbose and include irrelevant details. Which technique should be applied to encourage concise outputs?

Accepted Answer

Provide a few-shot example with concise summaries. Providing a few-shot example with concise summaries (Option A) directly demonstrates the desired output format to the model, leveraging in-context learning to bias generation toward brevity and relevance. This is the most effective technique for controlling output style without altering the model's underlying parameters.

Answer

Use chain-of-thought prompting

Answer

Decrease the top-k value

Answer

Increase the temperature

Question 11

A model trained on customer reviews achieves 98% accuracy on the test set. However, when deployed, it performs poorly on real-world data. The data scientist suspects distribution shift. Which action is MOST important to address this?

Accepted Answer

Implement a monitoring system to detect data drift and retrain with fresh data. Distribution shift (data drift) causes the model's training distribution to differ from the real-world distribution, degrading performance despite high test accuracy. Implementing a monitoring system to detect drift and retraining with fresh data directly addresses this by ensuring the model adapts to the current data distribution, which is the most critical action for maintaining performance in production.

Answer

Reduce the learning rate during training

Answer

Add more features to the model

Answer

Increase the number of cross-validation folds

Question 12

Which of the following is a key characteristic of Narrow AI (Weak AI)?

Accepted Answer

It is designed to excel at a single, specific task. Narrow AI, also known as Weak AI, is designed and trained to perform a single, specific task with high proficiency, such as language translation, image recognition, or playing chess. It cannot generalize its intelligence to other domains, which distinguishes it from Artificial General Intelligence (AGI). Option C correctly captures this fundamental characteristic.

Answer

It can perform any intellectual task that a human can

Answer

It requires no training data

Answer

It surpasses human intelligence in all domains

Question 13

A team is using a pre-trained BERT model for a sentiment analysis task on product reviews. They want to adapt it to their specific domain with limited labeled data. Which approach is MOST effective?

Accepted Answer

Fine-tune the pre-trained BERT model on the small labeled dataset. Fine-tuning the pre-trained BERT model on the small labeled dataset is the most effective approach because BERT has already learned rich language representations from large-scale corpora. Fine-tuning updates all or some of the pre-trained weights on the target task, allowing the model to adapt to the domain with limited data. This transfer learning approach consistently outperforms feature extraction and training from scratch when labeled data is scarce.

Answer

Use BERT as a feature extractor and train a logistic regression on top

Answer

Apply data augmentation to increase the dataset and then train from scratch

Answer

Train a new BERT model from scratch on the domain data

Question 14

An organization's AI system uses a decision tree model for loan approval. The compliance team requires explanations for each decision. Which property of decision trees makes them suitable for this requirement?

Accepted Answer

The decision rules are transparent and can be visualized as a tree. Decision trees inherently provide interpretable decision rules by splitting data based on feature thresholds at each node. The entire model can be visualized as a tree structure, allowing compliance teams to trace the exact path and logic behind each loan approval or rejection, which directly satisfies explainability requirements.

Answer

They can handle nonlinear relationships

Answer

They are robust to outliers

Answer

They can handle missing values

Question 15

A data scientist is building a recommendation system for an e-commerce platform. The dataset includes user purchase history, product descriptions, and user demographics. The goal is to recommend products that a user is likely to purchase. Which TWO techniques are most appropriate for this task? (Select TWO.)

Accepted Answer

Content-based filtering. Content-based filtering (A) is correct because it recommends items by matching a user's past purchase history against product descriptions, which is exactly the item-attribute data available here. Collaborative filtering (E) is correct because it leverages patterns across many users' purchase histories to recommend products a similar user is likely to buy, directly addressing the recommendation goal. Together these are the two standard recommender-system techniques suited to user purchase history, product descriptions, and demographics. Association rule mining (B) finds co-occurrence rules like market-basket pairs but does not personalize recommendations to a specific user. Linear regression (C) predicts a continuous numeric value and is not designed for ranking or recommending items. Anomaly detection (D) identifies outliers and is unrelated to generating product recommendations.

Answer

Association rule mining

Answer

Linear regression

Answer

Anomaly detection