Generative AI Leader Practice Question: Techniques to Improve Generative AI Model Output
A healthcare startup has fine-tuned a Vertex AI PaLM 2 model on a dataset of medical records to generate patient summaries. The model produces fluent text but occasionally fabricates diagnoses not present in the input. The team has already tried increasing the training data size by 20% and adjusting the temperature from 0.7 to 0.2, but hallucinations persist. The summaries must be factually accurate for regulatory compliance. What should the team do next?
⚠ Common exam trap
Many exam-takers assume adjusting model parameters (temperature, tokens) or switching models will fix hallucinations, when in fact the core issue is the lack of external knowledge grounding, which only RAG or similar retrieval-based techniques can reliably address for factual accuracy.
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
✓
Implement a RAG pipeline using Vertex AI Search to retrieve relevant medical documents before generation.
Implementing a Retrieval-Augmented Generation (RAG) pipeline with Vertex AI Search grounds the model's output in retrieved, authoritative medical documents. This directly addresses the root cause of hallucination—the model's reliance on its parametric memory—by providing factual context at inference time, which is far more effective for regulatory compliance than adjusting generation parameters or training data size alone.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Increase the maximum output tokens to allow the model to generate more detailed summaries.
Why it's wrong here
More tokens may increase the chance of hallucination.
- ✓
Implement a RAG pipeline using Vertex AI Search to retrieve relevant medical documents before generation.
Why this is correct
RAG provides grounded, up-to-date context, reducing hallucinations significantly.
- ✗
Add more few-shot examples to the prompt for each generation.
Why it's wrong here
Few-shot examples improve style but do not guarantee factual accuracy for unseen cases.
- ✗
Switch the base model to Gemini 1.5 Pro without additional changes.
Why it's wrong here
Changing the base model does not address the lack of grounding and may still hallucinate.
Go deeper
Related to this question
About these practice questions
One of 683 original Generative AI Leader practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This Generative AI Leader practice question is part of Courseiva's free Google Cloud 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 Generative AI Leader exam.