1Z0-1127-25 Fundamentals of Large Language Models Practice Question
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?
⚠ Common exam trap
Oracle often tests the misconception that simply filtering outputs or increasing model size can solve memorization and hallucination issues, when in fact only training-time techniques like differential privacy and inference-time grounding like RAG address the root causes.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
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 analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
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.
Why it's wrong here
Rule-based post-processing is inflexible and cannot handle novel PII or hallucinations. It also does not address the root cause of memorization.
- ✗
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.
Why it's wrong here
Switching to a larger model may increase memorization risk and does not inherently reduce hallucinations. Output filtering is reactive and may not catch all PII; differential privacy is a more robust approach.
- ✗
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.
Why it's wrong here
Increasing dataset size does not guarantee reduced memorization of specific records. Temperature 0 reduces randomness but does not prevent hallucination or memorization.
- ✓
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.
Why this is correct
Differential privacy during training reduces the risk of memorizing private data, and RAG grounds responses in a trusted knowledge base, reducing hallucinations. This combination addresses both issues effectively.
Go deeper
Related to this question
About these practice questions
This 1Z0-1127-25 question is part of Courseiva's 768-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam dumps. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This 1Z0-1127-25 practice question is part of Courseiva's free Oracle certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the 1Z0-1127-25 exam.