Question 1

2.2.2 A team uses few-shot prompting with three prior Gherkin examples to transform a new user story into Given-When-Then scenarios. The output includes steps covering both functional and negative paths. Which benefit is most likely achieved here?

Options :

A : Improved execution speed

B : Increased test environment stability

C : Reduced defect leakage through production

D : Higher coverage precision

Answer: D

Question 2

1.1.4 During a training exercise, a team is instructed to review and execute a prompt for a multimodal LLM. They must first inspect both an application screenshot and its textual requirements, then execute the prompt and verify results. What is the main goal of this exercise?

Options :

A : To practice manual visual comparison of UI elements

B : To demonstrate combined text and image input processing for testing

C : To fine-tune a vision-language model for a new dataset

D : To convert all visual data to textual descriptions before analysis

Answer: B

Question 3

1.1.4 A test engineer needs to identify mismatches between the expected UI layout described in user stories and screenshots from the latest build. They want to maximize test coverage by also generating additional test cases using the same model. Which approach is most suitable?

Options :

A : Use a multimodal LLM with a vision-language module

B : Use a reasoning LLM with chain-of-thought enabled

C : Use separate models for text and images, then combine results manually

D : Use a standard transformer trained only on text data

Answer: A

Question 4

1.1.3 A test automation team integrates an LLM into their defect triaging workflow. The initial implementation uses a model pre-trained on vast text, code, and image datasets without any fine-tuning. The team notices that while the model can categorize defects across multiple domains, it often fails to follow precise categorization rules provided in the prompt. Which type of LLM is most likely being used?

Options :

A : Instruction-tuned LLM

B : Reasoning LLM

C : Foundation LLM

D : Domain-specific symbolic AI

Answer: C

Question 5

2.2.1 A tester provides an LLM with regulatory compliance requirements, historical defect data, and business rules. Which GenAI-supported test analysis task is most directly enabled by this combination?

Options :

A : Identifying ambiguities in GUI layouts

B : Generating non-prioritized test conditions

C : Prioritizing test conditions based on risk level

D : Suggesting test techniques based solely on text patterns

Answer: C

Confidently Practice Online with Free CT-GenAI Exam Cram

Buying Options: