1Z0-1127-25 LLM Fundamentals Practice Question
Which TWO of the following are characteristics of decoder-only models like GPT? (Select TWO)
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
✓
They use masked self-attention to prevent attending to future tokens
Decoder-only models use masked self-attention (causal) and generate tokens left-to-right. They cannot use bidirectional context because future tokens are masked.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
They process input through an encoder and a decoder
Why it's wrong here
That describes encoder-decoder models, not decoder-only.
- ✗
They use bidirectional self-attention
Why it's wrong here
Decoder-only models use causal (unidirectional) attention, not bidirectional.
- ✓
They use masked self-attention to prevent attending to future tokens
Why this is correct
Masked self-attention ensures each token only attends to previous tokens.
- ✗
They are ideal for tasks requiring full bidirectional context like NER
Why it's wrong here
Bidirectional context is typical of encoder-only models (e.g., BERT), not decoder-only.
- ✓
They are typically used for generative tasks like text completion
Why this is correct
Decoder-only models are autoregressive and excel at text generation.
Go deeper
Related to this question
About these practice questions
One of 768 original 1Z0-1127-25 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 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.