MLA-C01 ML Model Development Practice Question
A data scientist wants to fine-tune a large language model for a question-answering task. They want to reduce memory usage during training by using a low-rank approximation of the weight updates. Which technique should they use?
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
✓
LoRA
LoRA (Low-Rank Adaptation) adds low-rank matrices to model weights, significantly reducing memory footprint while achieving competitive performance. QLoRA adds quantization for further reduction.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Full fine-tuning
Why it's wrong here
Full fine-tuning updates every model parameter, so optimiser state and gradients scale with total weights and memory usage stays high. It is tempting because it can yield the strongest task performance, and would be correct when memory is plentiful and maximum accuracy on the target task is the priority.
- ✗
Instruction tuning
Why it's wrong here
Instruction tuning changes the training data format to question-answer pairs but still updates the full weight set, so it does not reduce memory via low-rank approximation. It is tempting because it directly targets question-answering behaviour, and would be correct when adapting a base model to follow instructions rather than cutting memory.
- ✓
LoRA
Why this is correct
LoRA freezes the pretrained weights and injects trainable low-rank decomposition matrices into each layer, so only these small matrices receive gradient updates. This directly satisfies the stem's constraint of reducing memory usage via a low-rank approximation of weight updates during fine-tuning.
- ✗
RLHF
Why it's wrong here
RLHF optimises model behaviour against human preference rewards; it does not approximate weight updates. It is tempting because RLHF is used in LLM fine-tuning pipelines, but it addresses alignment, not memory reduction. LoRA, not RLHF, provides the low-rank update decomposition the scenario requires.
Go deeper
Related to this question
About these practice questions
This MLA-C01 question is part of Courseiva's 665-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 MLA-C01 practice question is part of Courseiva's free Amazon Web Services 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 MLA-C01 exam.