1Z0-1127-25 Practice Test 17 — 15 Questions

Question 1

Which of the following is the correct format for a training dataset used in OCI Generative AI fine-tuning?

Accepted Answer

JSONL file with 'prompt' and 'completion' fields. OCI GenAI fine-tuning expects a JSONL file with prompt/completion pairs.

Answer

CSV file with columns 'input' and 'output'

Answer

TXT file with one prompt-completion pair per line separated by a tab

Answer

Parquet file with 'text' and 'label' columns

Question 2

An application uses an LLM to summarize legal documents. The summaries sometimes include hallucinations (details not in the original text). Which prompt engineering technique is MOST effective at reducing hallucinations?

Accepted Answer

Include the full document text in the prompt and instruct the model to base its summary only on that text. Providing the full document context within the prompt (e.g., using a template that includes the document text) grounds the model's response and reduces the chance it invents details. Few-shot examples can also help but are secondary to providing the source.

Answer

Increase the temperature to 0.9 to make the model more cautious

Answer

Use a few-shot prompt with examples of correct summaries

Answer

Set the presence penalty to a high value

Question 3

A developer is using tree-of-thought prompting to solve a complex planning problem. Which THREE characteristics are typical of tree-of-thought?

Accepted Answer

It explores multiple reasoning branches in parallel. Tree-of-thought explores multiple reasoning branches in parallel, uses evaluation or heuristics to prune unpromising branches, and can backtrack to explore alternatives. It does not follow a single linear path or guarantee a single answer without voting.

Answer

It generates a single linear chain of reasoning

Answer

It always returns a single final answer via majority vote

Question 4

An administrator needs to ensure that only specific users in the finance department can invoke a generative AI model deployed on OCI. Which IAM policy should be used?

Accepted Answer

allow group finance_group to use generative-ai-model in compartment finance. The 'use' verb in an OCI IAM policy grants the minimum required permissions to invoke a generative AI model without allowing management actions like creating or deleting models. The policy scopes access to the 'finance_group' group and the 'finance' compartment, ensuring only specific users in the finance department can invoke the model.

Answer

allow group admins to use generative-ai-model in compartment finance

Answer

allow group finance_group to manage generative-ai-model in compartment finance

Answer

allow any-user to use generative-ai-model in compartment finance

Question 5

A company has deployed a generative AI model on OCI to generate product descriptions. After a recent update, the model started producing outputs with repetitive phrases and poor coherence. The inference endpoint is configured with default parameters. Which single parameter adjustment is most likely to improve output quality?

Accepted Answer

Increase the frequency penalty parameter to 0.5. Increasing the frequency penalty reduces the likelihood of the model repeating the same phrases, directly addressing the repetitive outputs. The frequency penalty subtracts a proportional penalty from tokens that have already appeared, discouraging repetition and improving coherence. Default parameters often have no frequency penalty (0.0), so a small positive value like 0.5 can significantly enhance output diversity.

Answer

Increase the max-tokens parameter to 512

Answer

Increase the temperature parameter to 1.5

Answer

Decrease the top-p parameter to 0.8

Question 6

A developer uses a Cohere Command model with a preamble: 'You are a helpful assistant that answers questions based on the provided document.' They also include a user message with a query and a relevant document excerpt. However, the model often ignores the document and uses its own knowledge. Which improvement is MOST effective?

Accepted Answer

Use the document-grounded generation format with and tags around the document. Cohere's document-grounded generation syntax uses special tags to clearly separate the document from the query, ensuring the model focuses on the provided content rather than its training data.

Answer

Increase the temperature to 0.7 to reduce reliance on parametric knowledge

Answer

Set frequency penalty to 0.5

Answer

Remove the preamble and rely solely on the user message

Question 7

Which TWO are advantages of using LoRA for fine-tuning?

Accepted Answer

Requires less GPU memory. LoRA (Low-Rank Adaptation) reduces GPU memory requirements because it freezes the original model weights and injects trainable low-rank matrices into specific layers. This means only a tiny fraction of parameters need gradients and optimizer states, drastically lowering memory consumption during fine-tuning compared to full fine-tuning.

Answer

Guarantees higher accuracy

Answer

Increases model size

Answer

Improves inference speed

Question 8

A data science team is using OCI Data Science to fine-tune a model. They notice that training jobs are failing due to out-of-memory errors on the notebook session. What should they do to resolve this?

Accepted Answer

Switch to a larger notebook session shape.. Out-of-memory errors during training on a notebook session indicate that the current shape's memory capacity is insufficient for the model or data being processed. Switching to a larger notebook session shape directly increases available RAM and compute resources, resolving the memory constraint without altering the training logic or infrastructure type.

Answer

Enable autoscaling on the notebook session.

Answer

Use OCI Data Flow instead.

Answer

Reduce the batch size in the training script.

Question 9

An LLM-based application must comply with data privacy regulations by not memorizing personally identifiable information (PII). Which technique best reduces memorization of PII?

Accepted Answer

Train with differential privacy. Differential privacy (DP) is the correct technique because it directly limits the model's ability to memorize training data, including PII, by adding calibrated noise to the gradient updates during training. This ensures that the model's parameters do not encode specific individual records, providing a formal mathematical guarantee against memorization. Other options like model size, temperature, or training epochs do not address the root cause of memorization in the training process.

Answer

Use a larger model with more parameters

Answer

Decrease the temperature during inference

Answer

Increase the number of training epochs

Question 10

A developer is using LangChain's ConversationBufferMemory to store chat history. They notice that after many turns, the prompt becomes too large and exceeds the model's context window. What is the BEST memory type to use for this scenario?

Accepted Answer

ConversationSummaryMemory. ConversationSummaryMemory periodically summarizes the conversation, keeping the prompt size manageable. It retains the gist of the conversation while reducing token usage.

Answer

ConversationEntityMemory

Answer

ConversationBufferMemory with a large max_token_limit

Answer

ConversationStringBufferMemory

Question 11

An organization needs to ensure that all inference requests to OCI Generative AI are logged for compliance. Which OCI feature should be enabled?

Accepted Answer

OCI Logging for the AI service. OCI Logging for the AI service captures detailed request and response data for inference calls to OCI Generative AI, including payloads, timestamps, and user identities. This feature must be explicitly enabled per service endpoint to meet compliance requirements for logging all inference requests. Unlike Audit logs, which record control-plane operations, OCI Logging provides data-plane logging for the AI service itself.

Answer

OCI Cloud Guard

Answer

OCI Vault

Answer

OCI Audit logs

Question 12

In LangChain's Expression Language (LCEL), what does the pipe (|) operator do when connecting components?

Accepted Answer

It passes the output of the left component as input to the right component. In LCEL, the | operator chains components by passing the output of the left component as input to the right component. This allows composing chains like prompt | model | output parser.

Answer

It conditionally selects one of the two components based on a flag

Answer

It repeats the left component's execution until a condition is met

Answer

It runs both components in parallel and merges their outputs

Question 13

An enterprise is building a document Q&A application with OCI Generative AI. They want to minimize hallucinations. Which TWO techniques should they implement? (Choose two.)

Accepted Answer

Fine-tune the model on domain-specific data. RAG grounds answers in retrieved documents, and fine-tuning on domain-specific data reduces errors. Increasing context window alone does not reduce hallucinations; greedy decoding reduces creativity but not factual errors.

Answer

Increase the model's context window to its maximum

Answer

Use a higher temperature in sampling

Answer

Apply greedy decoding

Question 14

A company wants to build a customer service chatbot that answers questions about their internal policy documents. The documents are updated monthly, and the team cannot afford to retrain a model each time. Which approach is MOST appropriate?

Accepted Answer

Use Retrieval-Augmented Generation (RAG) with the policy documents indexed in a vector store. RAG (Retrieval-Augmented Generation) allows the LLM to retrieve relevant document sections at inference time, so knowledge stays current without retraining. The other options either require expensive retraining for each update or lack document grounding.

Answer

Train a custom model from scratch on the policy documents each month

Answer

Use a larger foundation model with a longer context window and paste all documents into each prompt

Answer

Fine-tune a base LLM on the policy documents monthly

Question 15

A financial services company is concerned about data privacy when using OCI Generative AI service for processing sensitive customer data. They want to ensure that their data is not used to improve the model and is encrypted at rest and in transit. Which combination of OCI features should they implement?

Accepted Answer

Provision a dedicated endpoint, configure data privacy opt-out, and use OCI Vault for encryption keys. It addresses all three requirements: a dedicated endpoint ensures network isolation and encryption in transit, data privacy opt-out prevents OCI from using customer data for model improvement, and OCI Vault integration allows customers to manage their own encryption keys for data at rest, meeting the financial services company's strict data privacy and encryption needs.

Answer

Use OCI Object Storage buckets with encryption to store prompts and responses

Answer

Deploy the model in an OCI Data Science project with a private endpoint

Answer

Use the on-demand API with default encryption