1Z0-1127-25 Practice Test 49 — 15 Questions

Question 1

A data scientist is evaluating two LLMs for a summarization task. Model X scores 45 on ROUGE-L, while Model Y scores 42. However, in human evaluation, Model Y is preferred 60% of the time. What is the most likely explanation?

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

Accepted Answer

ROUGE-L measures lexical overlap, which may not capture the semantic quality that humans value. ROUGE-L measures the longest common subsequence (LCS) between generated and reference summaries, focusing on lexical (word-level) overlap. It does not assess semantic meaning, fluency, or factual correctness. Human evaluators often prefer summaries that are coherent and capture key ideas, even if they use different wording, which explains why Model Y can score lower on ROUGE-L but be preferred 60% of the time.

Answer

Human evaluators are biased and cannot be trusted for objective assessment

Answer

Model Y overfits to the training data, causing poor generalisation

Answer

ROUGE-L is not a reliable metric for summarization because it only measures recall

Question 2

A developer wants to invoke an OCI Generative AI model from an application running on a compute instance in OCI. The instance is in a private subnet. What is the most secure method to access the model endpoint?

Accepted Answer

Use a Service Gateway to access the endpoint privately.. A Service Gateway allows resources in a private subnet to access OCI services, including the Generative AI model endpoint, over the OCI private network without traversing the internet. This is the most secure method because traffic stays within the OCI backbone, avoiding exposure to public IPs and reducing the attack surface.

Answer

Use an Internet Gateway and public endpoint.

Answer

Use a VPN Connect to connect to the model's public IP.

Answer

Use a NAT Gateway to access the endpoint.

Question 3

A developer needs to authenticate API calls to OCI Generative AI from a compute instance. Which TWO methods can be used?

Accepted Answer

Configure an API key in OCI IAM for the user. An API key configured in OCI IAM for a user provides a standard way to authenticate API calls. The developer can generate a key pair (public/private) in IAM, then use the private key to sign requests to the OCI Generative AI service. This method is widely used for programmatic access from compute instances when the instance is acting on behalf of a specific user.

Answer

Configure a customer-managed key (CMK) for encryption

Answer

Set up a service connector to forward requests

Answer

Use an auth token from OCI Identity

Question 4

You are a machine learning engineer at a large e-commerce company. You have been tasked with deploying a large language model to power a customer service chatbot that handles product returns and refunds. The model will answer customer queries based on a knowledge base of return policies and FAQs. The company has strict requirements: (1) responses must be factually accurate and grounded in the knowledge base, (2) the system must be cost-effective, and (3) latency should be under 2 seconds per response. You decide to use a pre-trained LLM from OCI Data Science and implement retrieval-augmented generation (RAG). You have two options for the retriever: a dense embedding-based retriever (e.g., using OCI AI Language embeddings) or a sparse keyword-based retriever (e.g., BM25). You also need to decide on the generation model size: a 7B parameter model or a 70B parameter model. You run a pilot test: with the dense retriever + 7B model, average latency is 1.8 seconds and accuracy is 85%. With the sparse retriever + 7B model, latency is 1.2 seconds but accuracy drops to 75%. With the 70B model (any retriever), latency exceeds 5 seconds. Which combination should you choose to meet all requirements?

Accepted Answer

Dense retriever + 7B model.. (dense retriever + 7B model) is correct because it meets all three requirements: factual accuracy (85% accuracy from dense retrieval grounding), latency under 2 seconds (1.8 seconds), and cost-effectiveness (7B model is cheaper to run than 70B). The dense retriever provides better semantic matching for nuanced return policy queries, while the 7B model keeps inference fast and affordable.

Answer

Sparse retriever + 70B model.

Answer

Dense retriever + 70B model.

Answer

Sparse retriever + 7B model.

Question 5

A financial services company must deploy a fine-tuned model for transaction categorization. The model must be isolated from other tenants and provide predictable low-latency inference. The compliance team also requires that training data never leaves the OCI tenancy. Which THREE steps should the team take? (Choose three.)

Accepted Answer

Fine-tune the model using T-Few technique within OCI. A dedicated AI cluster provides isolation and predictable low latency. T-Few fine-tuning runs entirely within OCI, keeping data in tenancy. Model units are required for dedicated cluster provisioning. Shared infrastructure would compromise isolation. On-demand inference does not guarantee low latency.

Answer

Use OCI GenAI on-demand inference for the fine-tuned model

Answer

Host the model on a shared AI cluster to reduce cost

Question 6

A developer makes an API call to generate text with top_p=1.5. What is the correct way to fix this error?

Accepted Answer

Set top_p to a value between 0 and 1, e.g., 0.9. The `top_p` parameter, also known as nucleus sampling, must be a probability value between 0 and 1. Setting it to 1.5 is invalid because it exceeds the allowed range, which would cause the API to reject the request. The correct fix is to set `top_p` to a valid value such as 0.9, which restricts token selection to the smallest set whose cumulative probability exceeds that threshold.

Answer

Remove the top_p parameter from the request

Answer

Increase the temperature parameter to compensate

Answer

Use the top_k parameter instead

Question 7

A data scientist fine-tunes a model using OCI Data Science and wants to deploy it as a managed endpoint in OCI Generative AI. What must they do first?

Accepted Answer

Upload model artifacts to Object Storage and register in Model Catalog. To deploy a fine-tuned model as a managed endpoint in OCI Generative AI, the model artifacts must first be uploaded to Object Storage and registered in the Model Catalog. This is a prerequisite because OCI Generative AI endpoints pull model artifacts from the Model Catalog, which references the storage location. Without registration, the service cannot locate or serve the model.

Answer

Write a custom container

Answer

Create a dedicated AI cluster

Answer

Use OCI CLI to create an endpoint

Question 8

A data scientist is using OCI Data Science to fine-tune a Cohere command model on domain-specific documents. They observe that the fine-tuned model generates repetitive text. What is the most likely cause?

Accepted Answer

The training dataset lacked diversity.. Repetitive text in fine-tuned models is a classic symptom of overfitting to a narrow or homogeneous training dataset. When the domain-specific documents lack diversity in phrasing, topics, or contexts, the model learns to latch onto the most common patterns and repeats them, rather than generalizing. This is not a hyperparameter tuning issue but a data quality issue.

Answer

The number of epochs was insufficient.

Answer

The learning rate was too high.

Answer

The batch size was too small.

Question 9

Which of the following best describes the role of attention in transformer models?

Accepted Answer

It allows the model to focus on relevant parts of the input sequence when generating output.. The attention mechanism in transformer models dynamically computes a weighted sum of all input tokens, allowing the model to focus on the most relevant parts of the input sequence when generating each output token. This is achieved through scaled dot-product attention, which assigns higher weights to tokens that are more contextually important, enabling the model to capture long-range dependencies effectively.

Answer

It assigns equal weight to all words in the input.

Answer

It is used only during training, not inference.

Answer

It replaces the need for positional encoding.

Question 10

A developer is using Cohere Command R+ via OCI Generative AI and wants to ground answers in a provided set of documents using the `documents` parameter. Which prompt structure ensures the model correctly adheres to the documents?

Accepted Answer

Use a preamble: 'You answer questions based only on the provided documents. If the answer is not in the documents, say you don't know.' Then pass documents via the `documents` parameter in the request. Cohere's document-grounded generation requires the preamble to instruct the model to answer based solely on the documents, and the conversation history must include the documents in the correct format.

Answer

Set a system prompt that says 'You are a helpful assistant' and pass documents in the `documents` parameter with no further instruction

Answer

Place the documents in the conversation history as an assistant message before the user's question

Answer

Include the documents in the user message after the question

Question 11

An organization stores its knowledge base in Oracle Autonomous Database and wants to build a RAG chatbot using OCI Generative AI. The chatbot must retrieve the most relevant documents based on user queries. Which indexing approach is BEST suited for efficient similarity search on text embeddings?

Accepted Answer

Create an ANN index on the embedding vector column.. Approximate Nearest Neighbor (ANN) indexes are specifically designed for high-dimensional vector spaces, enabling efficient similarity search on embedding vectors. In Oracle Autonomous Database, ANN indexes (e.g., using IVF or HNSW algorithms) drastically reduce search latency compared to brute-force scans, which is critical for real-time RAG chatbot responses.

Answer

Create a bitmap index on the embedding vector column.

Answer

Create an inverted index on the document text column.

Answer

Create a B-tree index on the document text column.

Question 12

A company has fine-tuned a Cohere Command R model using T-Few and wants to deploy it for real-time inference with the lowest possible latency. They have provisioned a dedicated AI cluster with 2 model units. However, latency is still higher than expected. Which action is MOST likely to reduce latency?

Accepted Answer

Increase the number of model units on the dedicated AI cluster. Increasing model units on the dedicated cluster provides more compute capacity, reducing inference latency by parallelizing requests. Switching to shared infrastructure would likely increase latency due to multi-tenancy. Using a larger model would increase latency. Reducing temperature does not affect latency.

Answer

Reduce the temperature parameter to 0

Answer

Switch from dedicated AI cluster to shared infrastructure

Answer

Use a larger base model like Llama 3 70B

Question 13

An enterprise RAG system must ensure that retrieved data comes only from authorized sources. Which OCI feature should be used to enforce this?

Accepted Answer

OCI IAM policies for the vector database. OCI IAM policies allow you to define granular access controls on the vector database, ensuring that only authorized principals (users, groups, or service principals) can read or write data. This directly enforces that retrieved data comes only from authorized sources, which is a core requirement for enterprise RAG systems.

Answer

Data encryption at rest

Answer

Network security groups

Answer

Resource quotas

Question 14

A practitioner wants to generate embeddings for a set of legal documents to enable semantic search. Which type of model should they use?

Accepted Answer

An embedding model like Cohere Embed. Embedding models (e.g., Cohere Embed, OpenAI text-embedding-ada) are specialized to produce dense vector representations. Generation models (like GPT) produce text, not embeddings.

Answer

A large language model fine-tuned for classification

Answer

A vision transformer model

Answer

A generative LLM like Cohere Command

Question 15

A healthcare company is deploying OCI Generative AI Service for clinical decision support. They must ensure that model outputs are auditable, explainable, and free from patient data exposure. Which combination of OCI features should they use?

Accepted Answer

Use OCI Data Masking to de-identify inputs, and enable model monitoring with explainability outputs via OCI Monitoring and OCI Logging.. OCI Data Masking can de-identify patient data in inputs before they reach the generative AI model, ensuring no protected health information (PHI) is exposed. Enabling model monitoring with explainability outputs via OCI Monitoring and OCI Logging provides an auditable trail of model decisions and explanations, meeting the requirements for auditability and explainability in clinical decision support.

Answer

Fine-tune a model on de-identified patient notes and use default inference settings.

Answer

Use Retrieval-Augmented Generation with an internet search index for up-to-date medical knowledge.

Answer

Deploy the model in a private endpoint and disable all logging to prevent data leaks.