How does an LLM generate text one token at a time?

By translating the entire input sentence into a fixed output sentence.

By looking up the most frequent word in the training data.

By randomly selecting a token from the entire vocabulary without considering context.

By predicting the most likely next token based on the preceding context.

In software testing, which task is a typical use of an LLM's summarization capability?

Executing test scripts to verify application behavior.

Measuring the response time of an API endpoint.

Condensing a long bug report into a brief summary for quick review.

Allocating virtual machines for a test environment.

What is 'hallucination' in the context of LLMs?

The model refuses to answer a question due to safety guidelines.

The model provides answers only in a specific language.

The model generates plausible-sounding but factually incorrect or nonsensical information.

The model repeats the same response for different inputs.

A QA team wants to use an LLM to generate test case descriptions from user stories. They notice that the model sometimes produces test cases that include steps for features not mentioned in the story. What is the most likely cause of this behavior?

The model is hallucinating plausible-sounding but unsupported details based on patterns in its training data

The model is overfitting to the user story and memorizing test cases from its training set

The model is deliberately adding extra steps to make the test cases more comprehensive

The model has a bug in its tokenization algorithm that corrupts the user story input

A test team wants to use an LLM to generate test cases from user stories. The team also wants the LLM to answer questions about the test cases it generates. Which combination of LLM capabilities is being used?

Question answering and translation

Text generation and summarization

Text generation and question answering

Certified Tester Testing with Generative AI

Domain 1Objective 1

Basics of Generative AI and LLMs CT-GENAI Practice Questions (Page 6)

Part of the Introduction to Generative AI for Software Testing domain, which makes up ~12% of our current practice bank. ISTQB does not publish an official question count, but from its 60-minute exam (~25–40 total, ~3–5 in this domain), expect 1–1 from this objective — we provide 30 practice questions to prepare you well beyond it. (estimate)

30questions here

6free pages

7concepts

Questions 26–30

26foundation · easy
How does an LLM generate text one token at a time?
Select an answer first
27foundation · easy
In software testing, which task is a typical use of an LLM's summarization capability?
Select an answer first
28foundation · easy
What is 'hallucination' in the context of LLMs?
Select an answer first
29application · medium
A QA team wants to use an LLM to generate test case descriptions from user stories. They notice that the model sometimes produces test cases that include steps for features not mentioned in the story. What is the most likely cause of this behavior?
Select an answer first
30expert · medium
A test team wants to use an LLM to generate test cases from user stories. The team also wants the LLM to answer questions about the test cases it generates. Which combination of LLM capabilities is being used?
Select an answer first

Finished these 5 questions?

Review the revealed explanations, or continue through the curriculum.

No more pagesBack to CT-GENAI

Free Basic Practice is a study aid with revealable answers — not a scored exam. Examers.io is independent and not affiliated with or endorsed by ISTQB. “CT-GENAI” is a trademark of its owner, used for identification only.