- A
It uses masked self-attention to prevent attending to future tokens
Causal masking ensures each token can only attend to previous tokens, which is essential for autoregressive generation.
- B
It generates text autoregressively, one token at a time
Decoder-only models predict the next token given all previous tokens in a left-to-right fashion.
- C
It uses bidirectional self-attention to capture context from both directions
Why wrong: Bidirectional attention is used in encoder-only models like BERT, not in decoder-only.
- D
It processes all tokens in parallel during generation
Why wrong: Generation is sequential; parallel processing is used only during training with teacher forcing.
- E
It implements cross-attention between encoder and decoder layers
Why wrong: Cross-attention is a feature of encoder-decoder architectures, not decoder-only.
1Z0-1127 LLM Fundamentals Practice Question
This 1Z0-1127 practice question tests your understanding of llm fundamentals. Read the scenario carefully and evaluate each option against the stated constraints before committing to an answer. After answering, compare your reasoning against the explanation and wrong-answer breakdown below. Once you have made your selection, read the full explanation to reinforce the concept and understand why each distractor is designed to mislead on exam day.
Which TWO of the following are characteristics of the transformer decoder-only architecture (e.g., GPT)?
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
It uses masked self-attention to prevent attending to future tokens
Option A is correct because the transformer decoder-only architecture, such as GPT, employs masked self-attention (also known as causal attention) to ensure that each token can only attend to previous tokens in the sequence. This masking prevents the model from 'seeing' future tokens during training and generation, which is essential for maintaining the autoregressive property where predictions depend only on past context.
Key principle: Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
It uses masked self-attention to prevent attending to future tokens
Why this is correct
Causal masking ensures each token can only attend to previous tokens, which is essential for autoregressive generation.
Related concept
Read the scenario before looking for a memorised answer.
- ✓
It generates text autoregressively, one token at a time
Why this is correct
Decoder-only models predict the next token given all previous tokens in a left-to-right fashion.
Related concept
Read the scenario before looking for a memorised answer.
- ✗
It uses bidirectional self-attention to capture context from both directions
Why it's wrong here
Bidirectional attention is used in encoder-only models like BERT, not in decoder-only.
- ✗
It processes all tokens in parallel during generation
Why it's wrong here
Generation is sequential; parallel processing is used only during training with teacher forcing.
- ✗
It implements cross-attention between encoder and decoder layers
Why it's wrong here
Cross-attention is a feature of encoder-decoder architectures, not decoder-only.
Common exam traps
Common exam trap: answer the scenario, not the keyword
Cisco often tests the distinction between attention mechanisms across architectures, and the trap here is that candidates confuse the parallel training capability (which is true for all transformers) with parallel generation (which is false for autoregressive models), leading them to incorrectly select Option D.
Detailed technical explanation
How to think about this question
Under the hood, masked self-attention in decoder-only models is implemented by applying a triangular mask (e.g., using an upper-triangular matrix of -inf) to the attention scores before the softmax operation, effectively zeroing out attention to future positions. This design allows the model to be trained on full sequences in parallel while still respecting causal dependencies, a technique known as 'teacher forcing' with masking. In real-world scenarios like GPT-4, this architecture enables efficient text generation for chat and completion tasks, but it also imposes a strict left-to-right context window that limits the model's ability to leverage bidirectional context without additional fine-tuning.
KKey Concepts to Remember
- Read the scenario before looking for a memorised answer.
- Find the constraint that changes the correct option.
- Eliminate answers that are true in general but not in this case.
TExam Day Tips
- Watch for words such as best, first, most likely and least administrative effort.
- Review why wrong options are wrong, not only why the correct option is correct.
Key takeaway
Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Real-world example
How this comes up in practice
A network engineer segments a warehouse floor into three subnets: 20 scanners, 5 printers, and 2 management hosts. Picking the wrong mask wastes addresses or leaves too few usable hosts. Exam questions test whether you can apply CIDR notation, calculate block size, and identify the correct usable-host range for a given prefix.
What to study next
Got this wrong? Here's your next step.
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
- →
LLM Fundamentals — study guide chapter
Learn the concepts, then practise the questions
- →
LLM Fundamentals practice questions
Targeted practice on this topic area only
- →
All 1Z0-1127 questions
991 questions across all exam domains
- →
Oracle Cloud Infrastructure Generative AI Professional 1Z0-1127 study guide
Full concept coverage aligned to exam objectives
- →
1Z0-1127 practice test guide
How to use practice tests most effectively before exam day
Related practice questions
Related 1Z0-1127 practice-question pages
Use these pages to review the topic behind this question. This is how one missed question becomes focused revision.
Prompt Engineering practice questions
Practise 1Z0-1127 questions linked to Prompt Engineering.
OCI Generative AI Service practice questions
Practise 1Z0-1127 questions linked to OCI Generative AI Service.
LLM Fundamentals practice questions
Practise 1Z0-1127 questions linked to LLM Fundamentals.
LangChain and AI Application Development practice questions
Practise 1Z0-1127 questions linked to LangChain and AI Application Development.
Fundamentals of Large Language Models practice questions
Practise 1Z0-1127 questions linked to Fundamentals of Large Language Models.
Using OCI Generative AI Service practice questions
Practise 1Z0-1127 questions linked to Using OCI Generative AI Service.
Building LLM Applications with RAG and Vector Search practice questions
Practise 1Z0-1127 questions linked to Building LLM Applications with RAG and Vector Search.
Deploying and Managing Generative AI on OCI practice questions
Practise 1Z0-1127 questions linked to Deploying and Managing Generative AI on OCI.
1Z0-1127 fundamentals practice questions
Practise 1Z0-1127 questions linked to 1Z0-1127 fundamentals.
1Z0-1127 scenario practice questions
Practise 1Z0-1127 questions linked to 1Z0-1127 scenario.
1Z0-1127 troubleshooting practice questions
Practise 1Z0-1127 questions linked to 1Z0-1127 troubleshooting.
Practice this exam
Start a free 1Z0-1127 practice session
Short sessions build daily habit. Longer sessions build exam-day stamina. Try a timed session to simulate real conditions.
FAQ
Questions learners often ask
What does this 1Z0-1127 question test?
LLM Fundamentals — This question tests LLM Fundamentals — Read the scenario before looking for a memorised answer..
What is the correct answer to this question?
The correct answer is: It uses masked self-attention to prevent attending to future tokens — Option A is correct because the transformer decoder-only architecture, such as GPT, employs masked self-attention (also known as causal attention) to ensure that each token can only attend to previous tokens in the sequence. This masking prevents the model from 'seeing' future tokens during training and generation, which is essential for maintaining the autoregressive property where predictions depend only on past context.
What should I do if I get this 1Z0-1127 question wrong?
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
What is the key concept behind this question?
Read the scenario before looking for a memorised answer.
About these practice questions
Courseiva creates original exam-style practice questions with explanations and wrong-answer analysis. It does not publish real exam questions, exam dumps, or protected exam content. Learn why practice questions differ from exam dumps →
Last reviewed: Jul 4, 2026
This 1Z0-1127 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 exam.
Question Discussion
Share a tip, memory trick, or ask about the reasoning behind this question. Do not post real exam questions, leaked content, braindumps, or copyrighted exam material. Comments are moderated and may be removed without notice.
Sign in to join the discussion.