mediumMultiple Choice
Generative AI Leader Practice Question: A researcher wants to adapt a large language…
A researcher wants to adapt a large language model for a specialized medical terminology domain without retraining the entire model. Which fine-tuning method is MOST parameter-efficient?
⚠ Common exam trap
Google often tests the distinction between 'fine-tuning' and 'prompt engineering'—the trap here is that candidates mistake in-context learning (Option A) for a fine-tuning method because it adapts behavior, but it does not update model parameters, making it ineligible as a parameter-efficient fine-tuning technique.
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
✓
Adapter-based fine-tuning using LoRA
LoRA (Low-Rank Adaptation) is the most parameter-efficient fine-tuning method because it injects trainable low-rank matrices into the transformer layers, updating only a tiny fraction (often <1%) of the model's parameters while keeping the original weights frozen. This allows the model to adapt to specialized medical terminology without the memory and compute cost of full fine-tuning, making it ideal for domain adaptation with limited resources.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
In-context learning with 50 examples
Why it's wrong here
In-context learning adds examples to the prompt without updating any weights, so it does not adapt the model's parameters to the medical domain at all. It is the right approach for quick, training-free task steering where domain-specific parameter adaptation is unnecessary.
- ✓
Adapter-based fine-tuning using LoRA
Why this is correct
LoRA freezes the pretrained weights and injects small trainable low-rank matrices into attention layers, so only a tiny fraction of parameters update. Adapters likewise add compact modules. This adapts the model to medical terminology while avoiding full retraining, satisfying the parameter-efficiency constraint.
- ✗
RLHF (Reinforcement Learning from Human Feedback)
Why it's wrong here
RLHF aligns model behaviour with human preferences and typically updates the full policy or a large reward model, so it is not parameter-efficient. It is the correct method when the objective is aligning outputs to human judgements rather than injecting specialised terminology.
- ✗
Full supervised fine-tuning of all model weights
Why it's wrong here
Full supervised fine-tuning updates all parameters, which for a large language model requires computational resources and training data far exceeding what is needed for a specialised medical domain. This method is tempting because it can achieve high task-specific accuracy when the target domain is large and diverse, and would be correct if the researcher had sufficient data and compute budget to retrain the entire model from scratch.
Go deeper
Related to this question
About these practice questions
This Generative AI Leader question is part of Courseiva's 1,008-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 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.