Generative AI Leader Practice Test 22 — 15 Questions

Question 1

A small business wants to use Vertex AI to analyze customer reviews and extract sentiment, product mentions, and overall themes. They have a small dataset of 500 reviews in a CSV file. The team is not experienced with machine learning and wants a pre-built solution that requires minimal coding. They want to start quickly and scale later. Which Google Cloud offering should they use?

Accepted Answer

Cloud Natural Language API for pre-trained sentiment and entity extraction.. Option C is correct. Vertex AI's Natural Language API offers pre-trained models for sentiment and entity extraction. Option A (Vertex AI Workbench) requires coding. Option B (AutoML) requires labeling and training. Option D (Gemini API) would require prompt engineering and is not purpose-built for this task.

Answer

Vertex AI Workbench to build a custom sentiment analysis model.

Answer

AutoML Natural Language to train a custom model on their data.

Answer

Vertex AI Gemini API with zero-shot prompting.

Question 2

A company notices that their AI chatbot occasionally generates incorrect information. Which technique can best reduce hallucinations without retraining?

Accepted Answer

Use system instructions to constrain the model to only answer from provided context. Using system instructions to constrain the model to the provided context directly reduces fabrication. Increasing temperature or setting top_p low would not specifically target hallucinations.

Answer

Use a longer system prompt without examples

Answer

Set top_p to 0.1

Answer

Increase temperature to 0.9

Question 3

A team wants to improve the factual accuracy of their chatbot responses regarding internal company policies. What is the most effective approach?

Accepted Answer

Use RAG with Vertex AI Search indexing the policies. RAG with Vertex AI Search retrieves current policy documents, providing authoritative context. Fine-tuning may not capture frequent updates, and other options do not integrate live knowledge.

Answer

Use few-shot prompting with example Q&A pairs

Answer

Increase the model's maximum tokens

Answer

Fine-tune the model on policy documents

Question 4

A real-time customer support chatbot using Gemini is experiencing high latency. The team must maintain response quality while improving speed. Which technique should they implement?

Accepted Answer

Use context caching for frequent queries. Context caching reuses context from common intents, reducing processing time without sacrificing quality. Temperature changes or larger models would not help latency or quality.

Answer

Switch to a larger model

Answer

Increase the batch size

Answer

Decrease the temperature

Question 5

A marketing company wants to fine-tune a generative AI model to adopt a specific brand voice. Which tuning method is most appropriate?

Accepted Answer

Supervised fine-tuning with labeled examples of the brand voice. Supervised fine-tuning with labeled examples directly teaches the desired style. RLHF is for broader alignment, and grounding or prompt engineering are not as precise for tone.

Answer

RLHF with general user feedback

Answer

Grounding with external knowledge base

Answer

Prompt engineering with system instructions

Question 6

Despite applying safety filters, a generative AI model still produces toxic outputs in some cases. Which additional technique should be applied?

Accepted Answer

Use RLHF with human feedback to reduce toxicity. RLHF using human feedback to penalize toxic responses directly reduces such outputs. Other options either weaken safety or do not target toxicity specifically.

Answer

Add more examples of toxic content to training

Answer

Increase the filter threshold

Answer

Decrease the model's temperature

Question 7

For a document summarization task, a team wants to produce concise summaries without losing key information. Which combination of techniques is most effective?

Accepted Answer

Use few-shot examples and reduce max output tokens. Using few-shot examples teaches the desired format, and reducing max tokens enforces conciseness. Other options either encourage verbosity or are off-target.

Answer

Set top_p to 0.5 and increase repetition penalty

Answer

Use prompt caching and increase batch size

Answer

Increase temperature and use a larger model

Question 8

Which THREE are best practices for designing prompts for a generative AI model?

Accepted Answer

Provide few-shot examples for complex tasks. Clear instructions, few-shot examples, and task decomposition improve the model's understanding and output quality. Negative prompting is less reliable, and fixed temperature is not a universal best practice.

Answer

Use negative prompts to avoid undesired outputs

Answer

Always set temperature to 1.0 for creativity

Question 9

Which TWO are advantages of using Retrieval-Augmented Generation (RAG) over fine-tuning?

Accepted Answer

No need to retrain the base model. RAG doesn't require retraining and is easy to update with new information. Inference latency is typically higher for RAG due to retrieval, and data preparation is still needed for indexing.

Answer

Requires less data preparation

Answer

Lower inference latency

Answer

More secure because model weights are not modified

Question 10

Refer to the exhibit. A team attempted to start a model tuning job but received the error 'Quota limit exceeded for tuning jobs in region us-central1'. What is the most appropriate action?

Accepted Answer

Request a quota increase for tuning jobs in us-central1. The error indicates that the quota for tuning jobs in us-central1 has been reached. Requesting a quota increase directly addresses the issue. Using a different region or model might work but is not the first recommended step.

Answer

Change the region to us-west1 and retry

Answer

Reduce the size of the training data

Answer

Use a different base model

Question 11

Refer to the exhibit. A Vertex AI endpoint configured with the above deployment is returning HTTP 429 (Too Many Requests) errors during peak traffic. The current CPU utilization reaches 80% consistently. What should the team adjust to resolve this?

Accepted Answer

Increase maxReplicaCount to 10. 429 errors indicate insufficient capacity. Increasing maxReplicaCount allows more replicas to be added when load increases. Changing machine type or scale target would not directly address the capacity shortage.

Answer

Increase scaleTarget to 0.9

Answer

Change machineType to n1-highmem-2

Answer

Increase minReplicaCount to 2

Question 12

Refer to the exhibit. A user wants formal translations from a generative AI model, but the model outputs informal style inconsistently. Which prompt engineering technique would best ensure consistent formal translations?

Accepted Answer

Provide a few-shot example with formal and informal pairs. Providing a few-shot example that explicitly demonstrates the desired formal translation guides the model to follow that pattern. System instructions can help but are less direct.

Answer

Use context caching

Answer

Use a longer system prompt with detailed rules

Answer

Set top_k to 1

Question 13

A company is prompt engineering a model for customer support. They want to reduce hallucination (false information) in responses. Which TWO techniques are most effective? (Choose two.)

Accepted Answer

Implement RAG to retrieve relevant documents for context. Correct options: B and D. B (Retrieval-Augmented Generation) grounds the model in real data. D (specify in system instruction to only use provided facts) instructs the model to rely on context. A (increase temperature) increases creativity, worsening hallucination. C (few-shot examples) helps format but not factuality. E (reduce max tokens) only limits length.

Answer

Provide 3 few-shot examples of conversations

Answer

Reduce max output tokens to 150

Answer

Increase temperature to 1.2

Question 14

A model generates biased output. Which technique is least effective?

Accepted Answer

Set frequency penalty to 1.0. Setting frequency penalty to 1.0 reduces token repetition but does not address bias. Fine-tuning on diverse data, adversarial debiasing, and safety filters all directly tackle bias.

Answer

Use adversarial debiasing

Answer

Apply safety filters

Answer

Fine-tune on diverse data

Question 15

A healthcare organization needs a generative AI model to answer medical questions using proprietary clinical guidelines. They have a large dataset of doctor-patient interactions. Should they fine-tune a pre-trained model or use Retrieval-Augmented Generation (RAG)?

Accepted Answer

Use RAG to retrieve relevant guidelines during inference, avoiding frequent retraining.. RAG is preferred because it can incorporate the latest guidelines without retraining, crucial for regulatory changes. Fine-tuning may cause overfitting to outdated interactions. Option B is wrong because fine-tuning requires continuous retraining. Option C is wrong because prompt engineering alone cannot inject proprietary knowledge. Option D is wrong because RAG does not inherently reduce cost.

Answer

Use RAG to reduce inference costs by skipping model updates.

Answer

Use prompt engineering to encode all guidelines into the system prompt.

Answer

Fine-tune the model on the clinical guidelines and interactions.