1Z0-1127-25 Fundamentals of Large Language Models Practice Test 4 — 15 Questions

Question 1

A healthcare startup is building a chatbot to answer patient inquiries using a large language model (LLM) deployed on OCI Data Science AI Quick Actions. The chatbot must comply with HIPAA regulations, so all patient data must remain within the OCI tenancy and never be sent to third-party APIs. The team has fine-tuned a Llama 2 7B model on de-identified medical records using OCI Data Science notebooks. The model is deployed as a managed endpoint via AI Quick Actions. Early testing shows that the chatbot sometimes generates responses containing specific patient names or dates of birth that were present in the fine-tuning dataset. Moreover, the model occasionally hallucinates medication dosages that are not medically accurate. Which course of action should the team take to address both issues while maintaining HIPAA compliance?

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

Accepted Answer

Re-fine-tune the model using differential privacy to limit memorization of training data, and implement retrieval-augmented generation (RAG) with a curated medical knowledge base to ground medication-related responses.. It addresses both memorization of PII and hallucination of medication dosages while maintaining HIPAA compliance. Differential privacy during fine-tuning limits the model's ability to memorize specific patient data, and retrieval-augmented generation (RAG) grounds responses in a curated medical knowledge base, reducing hallucinations without sending data outside the OCI tenancy.

Answer

Deploy a rule-based post-processing script that checks each response against a list of known patient names and medication dosages, and rejects any response containing them.

Answer

Switch to a larger model (e.g., Llama 2 70B) to improve accuracy and reduce hallucinations, and apply output filtering to remove any detected PII from responses.

Answer

Increase the fine-tuning dataset size with more varied de-identified records to reduce overfitting, and apply a temperature setting of 0 to make outputs deterministic.

Question 2

A company wants to build a customer support chatbot using OCI Generative AI. They have a large number of historical support tickets. Which approach is most effective for leveraging this data to improve the chatbot's responses?

Accepted Answer

Fine-tune the Cohere Command model on the historical tickets using OCI Data Science.. Fine-tuning the Cohere Command model on the historical support tickets using OCI Data Science is the most effective approach because it adapts the model's weights to the specific domain language, terminology, and resolution patterns found in the company's data. This supervised learning process creates a specialized model that can generate accurate, context-aware responses for customer support queries, unlike generic prompting methods that lack deep domain adaptation.

Answer

Use a pre-loaded prompt template from the OCI console.

Answer

Increase the temperature parameter to 1.0 to encourage diverse responses.

Answer

Use zero-shot prompting with the base model and include few-shot examples in the prompt.

Question 3

A developer is using the OCI Generative AI API to generate text. The responses are often too short and incomplete. Which parameter adjustment is most likely to produce longer, more complete responses?

Accepted Answer

Increase the max_tokens parameter.. The max_tokens parameter controls the maximum number of tokens (words or subwords) the model can generate in a single response. By increasing max_tokens, the model is allowed to produce longer sequences, which directly addresses the issue of responses being too short and incomplete. In the OCI Generative AI API, this is the primary parameter for capping output length.

Answer

Decrease the max_tokens parameter.

Answer

Increase the top_p parameter.

Answer

Decrease the frequency_penalty parameter.

Question 4

During fine-tuning of a large language model on OCI, you notice that the model's performance on the validation set is not improving after several epochs, but the training loss continues to decrease. What is the most likely cause?

Accepted Answer

The model is overfitting to the training data.. When training loss decreases but validation performance stagnates or worsens, the model is overfitting to the training data. It memorizes the training examples but fails to generalize. A high learning rate might cause divergence, not this pattern. Too small training data can contribute to overfitting but is not the direct symptom. An unrepresentative validation set could cause mismatch, but the described pattern is classic overfitting.

Answer

The learning rate is too high.

Answer

The validation set is not representative.

Answer

The training data is too small.

Question 5

A user wants to use OCI Generative AI to generate marketing copy. They want the output to be more creative and varied. Which parameter should they adjust?

Accepted Answer

Increase the temperature parameter.. Increasing the temperature parameter makes the model's output more random and diverse, which is ideal for creative tasks like generating marketing copy. A higher temperature (e.g., 0.7–1.0) increases the probability of sampling less likely tokens, leading to more varied and imaginative text. Setting temperature to 0 would make the output deterministic and repetitive, which is the opposite of what the user wants.

Answer

Set temperature to 0.

Answer

Decrease the temperature parameter.

Answer

Increase the max_tokens parameter.

Question 6

An organization is concerned about the safety of generated content. Which OCI feature allows them to define custom policies to block inappropriate outputs?

Accepted Answer

Content filtering and safety controls in Generative AI. OCI Generative AI includes built-in content filtering and safety controls that allow organizations to define custom policies to block inappropriate or harmful outputs. These controls operate at the model inference layer, enabling fine-grained filtering based on categories such as toxicity, hate speech, or personally identifiable information (PII). This directly addresses the concern about generated content safety.

Answer

OCI IAM policies

Answer

OCI Audit logs

Answer

OCI Vault

Question 7

A data scientist is using the OCI Generative AI SDK to create embeddings for a large corpus of legal documents. They want to perform semantic search. Which endpoint should they use?

Accepted Answer

/v1/embed. The /v1/embed endpoint is specifically designed to generate vector embeddings from input text, which are numerical representations that capture semantic meaning. For semantic search over a large corpus of legal documents, embeddings must be created to enable similarity comparisons, making this the correct choice.

Answer

/v1/classify

Answer

/v1/generate

Answer

/v1/chat

Question 8

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 9

A company wants to deploy a private instance of a large language model on OCI for sensitive data processing. What is the recommended approach?

Accepted Answer

Use OCI Dedicated AI Clusters for a private endpoint.. OCI Dedicated AI Clusters provide a fully isolated, private endpoint for deploying large language models, ensuring that sensitive data never traverses the public internet. This approach meets the requirement for private inference with no data leaving the customer's tenancy, unlike public endpoints or third-party hosting.

Answer

Use OCI Data Science with a publicly accessible model.

Answer

Use the OCI Generative AI public endpoint with data encryption.

Answer

Use third-party model hosting outside OCI.

Question 10

During inference with OCI Generative AI, you notice that the model is generating repetitive phrases. Which combination of parameters can help reduce repetition?

Accepted Answer

Top_p = 0.9, frequency_penalty = 0.5. A high Top_p value (0.9) allows the model to consider a diverse set of tokens, reducing the chance of getting stuck in repetitive loops, while a positive frequency_penalty (0.5) actively penalizes tokens that have already been generated, discouraging the model from repeating the same phrases. Together, these parameters balance creativity and repetition suppression.

Answer

Top_p = 0.1, frequency_penalty = 0.5

Answer

Top_p = 0.9, frequency_penalty = 0.0

Answer

Top_p = 1.0, frequency_penalty = 0.0

Question 11

A data scientist is evaluating different models for a summarization task. Which two metrics are commonly used to evaluate the quality of generated summaries?

Accepted Answer

ROUGE. ROUGE (Recall-Oriented Understudy for Gisting Evaluation) is a standard metric for summarization that measures the overlap of n-grams, word sequences, or word pairs between the generated summary and reference summaries. It focuses on recall, making it well-suited for evaluating how well the generated summary captures the key content from the reference.

Answer

F1 score

Answer

Mean Average Precision

Answer

Perplexity

Question 12

An organization is planning to use OCI Generative AI for sensitive customer data. Which three OCI services or features should they consider for data governance and security?

Accepted Answer

OCI Vault for managing API keys. OCI Vault is a dedicated service for securely storing and managing secrets, including API keys used to authenticate to OCI Generative AI. By centralizing API key management in Vault, organizations can enforce rotation policies, access controls, and audit trails, which is critical for protecting sensitive customer data when invoking generative AI models.

Answer

OCI Data Safe for data masking and encryption

Answer

OCI Data Labeling for annotating data

Question 13

Refer to the exhibit. A developer runs this command and sees that the 'cohere.embed-english-v3.0' model is INACTIVE. What is the most likely cause?

Accepted Answer

The model has been deprecated and is no longer available.. The 'cohere.embed-english-v3.0' model is listed as INACTIVE because Oracle Cloud Infrastructure (OCI) has deprecated it, meaning it is no longer available for inference. When a model is deprecated, its status changes to INACTIVE, and any attempt to invoke it will fail, even if the region, policies, and compartment permissions are correctly configured.

Answer

The model is not supported in the current region.

Answer

The API call lacks the required OCI policy for the model.

Answer

The compartment does not have access to the model.

Question 14

Refer to the exhibit. A developer encounters this error. Which action should they take to resolve the issue?

Accepted Answer

Wait and retry after some time.. The error indicates a rate limit or throttling issue, typically returned by the OCI Generative AI service when the API request quota is exceeded. Waiting and retrying after the cooldown period allows the rate limit to reset, which is the correct resolution for transient throttling errors.

Answer

Change the model to cohere.command-light.

Answer

Increase the max-tokens value.

Answer

Decrease the temperature to 0.0.

Question 15

Refer to the exhibit. A user in group GenAIUsers reports that they cannot call the OCI Generative AI API. What is the most likely issue?

Accepted Answer

The compartment ID in the policy does not match the user's compartment.. The policy is scoped to a specific compartment ID, but the user's compartment does not match that ID. For OCI IAM policies to grant access to resources like the Generative AI API, the policy must be written for the compartment where the resource resides or where the user operates. Since the user is in a different compartment, the policy does not apply, causing the API call to fail.

Answer

The policy statement is missing the 'inspect' verb.

Answer

The policy is in INACTIVE state.

Answer

The user is not in the group GenAIUsers.