1Z0-1127-25 Fundamentals of Large Language Models Practice Test 8 — 15 Questions

Question 1

The job fails with "InvalidParameter: trainingDatasetUri". What should the administrator check first?

Accepted Answer

Whether the bucket exists and the file is accessible.. The error 'InvalidParameter: trainingDatasetUri' indicates that the URI provided for the training dataset is invalid or inaccessible. In OCI Generative AI service, the training dataset must be stored in an OCI Object Storage bucket, and the URI must point to an existing, readable file. Therefore, the administrator should first verify that the bucket exists and the file is accessible, as this is the most common cause of this error.

Answer

Whether the compartment has sufficient budget.

Answer

Whether the model ID supports fine-tuning.

Answer

Whether the parameters JSON is correctly formatted.

Question 2

An OCI GenAI practitioner wants to deploy a model that can generate code from natural language descriptions. Which type of model is most suitable?

Accepted Answer

GPT. GPT (Generative Pre-trained Transformer) is the most suitable model for code generation from natural language because it is an autoregressive language model optimized for text generation tasks. Unlike encoder-only models, GPT generates coherent, contextually relevant sequences of tokens, making it ideal for producing code based on descriptive prompts.

Answer

T5

Answer

ResNet

Answer

BERT

Question 3

A developer runs an OCI GenAI chat request with system prompt "You are a sarcastic assistant." The output is offensive. How can the developer enforce safety policies?

Accepted Answer

Use the OCI GenAI content moderation filter.. The OCI GenAI content moderation filter is specifically designed to enforce safety policies by detecting and blocking offensive, harmful, or policy-violating content in both input prompts and model outputs. By enabling this filter, the developer can prevent the model from generating offensive responses even when a system prompt like 'You are a sarcastic assistant' encourages undesirable behavior.

Answer

Change model to LLAMA.

Answer

Increase maxTokens.

Answer

Set temperature to 0.

Question 4

A data engineer wants to migrate a large corpus of PDFs to OCI for use with GenAI. Which storage and preprocessing approach is most efficient for RAG?

Accepted Answer

Store PDFs in OCI Object Storage, then use OCI AI Document Understanding to extract text and create embeddings.. OCI Object Storage is optimized for large-scale, unstructured data like PDFs, and OCI AI Document Understanding provides a managed service to extract text from PDFs, which can then be directly fed into embedding pipelines for RAG. This eliminates the need for manual preprocessing or local compute, ensuring scalability and integration with GenAI services.

Answer

Convert PDFs to text locally, upload to OCI Database, use SQL queries to retrieve.

Answer

Use OCI Data Flow to process in batch and store in NoSQL.

Answer

Store PDFs in OCI File Storage, mount to compute, run offline extraction.

Question 5

A developer is using OCI GenAI to generate structured data. They often get responses that include additional commentary or markdown. Which prompt engineering technique should they use to ensure only JSON output?

Accepted Answer

Add 'Return only JSON' at the end of the prompt.. Explicitly instructing the model to 'Return only JSON' directly constrains the output format, reducing the likelihood of extraneous commentary or markdown. This technique leverages prompt engineering to guide the model's behavior without altering inference parameters like temperature or top_p, which control randomness rather than output structure.

Answer

Set top_p to 0.1.

Answer

Use a model with a larger context window.

Answer

Increase the temperature to 1.5.

Question 6

A startup needs to deploy an LLM for a simple FAQ chatbot on OCI with low latency. Which model choice is most appropriate?

Accepted Answer

Use a smaller, task-specific fine-tuned model.. For a simple FAQ chatbot requiring low latency, a smaller, task-specific fine-tuned model is most appropriate because it reduces inference time and computational overhead while maintaining high accuracy on the narrow domain of FAQs. Fine-tuning adapts the model to the specific question-answer patterns, avoiding the unnecessary complexity and latency of larger general-purpose models.

Answer

Use a medium-sized model with high precision.

Answer

Use an ensemble of models.

Answer

Use the largest available model for best quality.

Question 7

A company wants to create a chatbot that answers questions based on a large internal document set that is updated weekly. They have limited ML expertise. Which approach is recommended?

Accepted Answer

Use retrieval-augmented generation (RAG) with a vector database.. Retrieval-Augmented Generation (RAG) with a vector database is the recommended approach because it allows the chatbot to answer questions based on a large, frequently updated document set without requiring model retraining. RAG retrieves relevant document chunks at query time using vector similarity search, then passes them as context to the LLM, ensuring up-to-date answers with minimal ML expertise.

Answer

Fine-tune a model on the entire document set.

Answer

Train a custom model from scratch.

Answer

Include all documents in the system prompt.

Question 8

A multi-turn chatbot needs to maintain context across user queries. The context window is limited. What design should be used?

Accepted Answer

Use a summary of previous turns and add new input.. Summarizing previous turns and appending the new input efficiently manages the limited context window of large language models (LLMs). This approach preserves essential conversational context without exceeding token limits, ensuring coherent multi-turn interactions.

Answer

Store context in a separate database and retrieve each time.

Answer

Reset context after each turn.

Answer

Keep the entire conversation history in each request.

Question 9

A financial institution uses an LLM for generating investment advice. They are concerned about hallucinations. Which method is most effective?

Accepted Answer

Use RAG with a verified corpus of regulations and reports.. Retrieval-Augmented Generation (RAG) grounds the LLM's output in a verified, external knowledge base (e.g., regulations and reports). By retrieving relevant documents at inference time, RAG reduces the model's reliance on its parametric memory, directly mitigating hallucinations in high-stakes domains like financial advice.

Answer

Fine-tune on general financial data.

Answer

Increase the temperature to get more creative responses.

Answer

Use a larger model to improve accuracy.

Question 10

A development team wants to generate code snippets from natural language. Which model strategy should they adopt?

Accepted Answer

Use a code-specific model like Code Llama.. Code Llama is a specialized variant of Llama 2 that has been fine-tuned on code datasets, enabling it to generate syntactically and semantically correct code from natural language prompts. This makes it the optimal choice for code generation tasks, as general-purpose LLMs lack the targeted training on code structures and programming languages.

Answer

Use a general-purpose LLM like Llama 2.

Answer

Use a multimodal model.

Answer

Use an embedding model for text.

Question 11

An AI assistant needs to solve complex math word problems step by step. Which prompting technique is most suitable?

Accepted Answer

Chain-of-thought prompting with few-shot examples.. Chain-of-thought prompting with few-shot examples is most suitable because it guides the LLM to break down complex math word problems into intermediate reasoning steps, mimicking human problem-solving. Few-shot examples provide a template for the desired reasoning structure, which significantly improves accuracy on multi-step arithmetic tasks compared to direct answer generation.

Answer

Zero-shot prompting with the problem only.

Answer

Prompting with a high temperature setting.

Answer

Using a model with a larger context window.

Question 12

Which two are essential components of the Transformer architecture? (Select TWO)

Accepted Answer

Self-attention mechanism. The self-attention mechanism (C) is essential because it is the core operation that lets each token attend to every other token in the sequence, computing scaled dot-product attention (softmax(QK^T/√d_k)V) to capture contextual relationships in parallel. The feed-forward neural network (D) is also essential, as each Transformer block applies a position-wise fully connected network (typically two linear layers with a ReLU/GELU activation) after the attention sublayer to add non-linear transformation capacity. Together with residual connections and layer normalization, these two components form the standard encoder/decoder block. Pooling layers (A) are not required—Transformers use attention rather than pooling for aggregation, and pooling appears mainly in CNNs. Recurrent connections (B) belong to RNNs/LSTMs, which Transformers replaced by removing sequential recurrence. Convolutional layers (E) are characteristic of CNNs, not the standard Transformer block.

Answer

Pooling layers

Answer

Recurrent connections

Answer

Convolutional layers

Question 13

A developer integrates OCI GenAI into a mobile app to provide product descriptions. The responses sometimes include explanations or questions instead of the requested format. The developer is using a simple prompt: 'Describe product X.' The app expects a single paragraph. Which corrective action should the developer take?

Accepted Answer

Add a structured prompt with format instructions and an example.. Adding a structured prompt with format instructions and an example directly addresses the issue of the model producing off-format responses. By explicitly specifying the expected output (e.g., 'Provide a single paragraph description without questions or explanations') and including a few-shot example, the developer constrains the model's generation to match the desired format, leveraging prompt engineering to guide the LLM's behavior without changing model parameters or architecture.

Answer

Lower the temperature to 0 to make responses deterministic.

Answer

Increase the max tokens to allow longer responses.

Answer

Switch to a different model with better language understanding.

Question 14

A customer support company uses Cohere Command on OCI to answer user queries. They have enabled grounding with a knowledge base of product manuals. However, for about 20% of queries, the model provides incorrect product recommendations that are not in the manuals. The team has verified the knowledge base is up to date. What is the most likely cause and solution?

Accepted Answer

The query phrasing may not match the knowledge base; improve the retrieval system or use query rewriting.. Grounding with a knowledge base works by retrieving relevant documents based on the user's query, then conditioning the model's response on those documents. If the query phrasing does not semantically match the content in the manuals (e.g., using synonyms, different terminology, or vague language), the retrieval step may fail to fetch the correct passages. The model then generates an answer without proper grounding, leading to incorrect recommendations. Improving the retrieval system (e.g., using better embeddings, hybrid search) or applying query rewriting to align the query with the knowledge base can fix this.

Answer

The model's temperature is too high, causing creative responses. Lower temperature to 0.

Answer

The model is hallucinating; switch to a larger model.

Answer

The grounding settings are too restrictive; increase the number of retrieved documents.

Question 15

A company is building a chatbot using OCI Generative AI service. They want to ensure that the model responses are grounded in their internal knowledge base. Which approach should they use?

Accepted Answer

Retrieval-Augmented Generation (RAG). Retrieval-Augmented Generation (RAG) is the correct approach because it retrieves relevant documents from the company's internal knowledge base at inference time and provides them as context to the LLM, ensuring the model's responses are grounded in verifiable, up-to-date information without modifying the model itself. This directly addresses the requirement to ground responses in an internal knowledge base while avoiding the cost and complexity of retraining.

Answer

Prompt engineering with few-shot examples

Answer

Fine-tuning the model on the internal knowledge base

Answer

Model distillation to compress the knowledge base