DatabricksCertified Generative AI Engineer Associate
Domain 6Objective 1
Evaluation Metrics and Model Selection GENERATIVE-AI-ENGINEER-ASSOCIATE Practice Questions (Page 4)
Part of the Section 6: Evaluation and Monitoring domain, which makes up ~17% of our current practice bank. Databricks does not publish an official question count, but from its 90-minute exam (~35–60 total, ~6–10 in this domain), expect 1–2 from this objective — we provide 19 practice questions to prepare you well beyond it. (estimate)
19questions here
4free pages
3concepts
Questions 16–19
- 16
A team is evaluating an LLM for a question-answering system over a fixed set of documents. They have a test set of questions with known correct answers. The team wants a metric that measures the proportion of questions for which the model's answer exactly matches the reference answer. Which metric is most appropriate?
Select an answer first - 17
A company is deploying an LLM for a document classification task where each document must be assigned to one of 10 predefined categories. The dataset is imbalanced, with one category representing 80% of the documents. The team needs to select a metric to compare candidate models. Which metric is most appropriate?
Select an answer first - 18
A financial services company deploys a customer-facing chatbot that answers questions about account balances and recent transactions. The chatbot uses a retrieval-augmented generation (RAG) pipeline over a knowledge base of product documents. The compliance team requires that the chatbot never fabricates account-specific information. Which metric should the team prioritize when evaluating the chatbot's responses?
Select an answer first - 19
A media company deploys an LLM to generate news article headlines. The team wants to ensure the headlines are catchy and engaging, but also accurate and not misleading. Which combination of metrics should the team monitor?
Select an answer first
Finished these 4 questions?
Review the revealed explanations, or continue through the curriculum.
No more pagesBack to GENERATIVE-AI-ENGINEER-ASSOCIATE
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 Databricks. “GENERATIVE-AI-ENGINEER-ASSOCIATE” is a trademark of its owner, used for identification only.