ExamTopics Logo
Mail Us[email protected]
Menu
Databricks Discussions
exam questions

Exam Certified Generative AI Engineer Associate All Questions

View all questions & answers for the Certified Generative AI Engineer Associate exam
Go to Exam

Exam Certified Generative AI Engineer Associate topic 1 question 15 discussion

Actual exam question from Databricks's Certified Generative AI Engineer Associate
Question #: 15
Topic #: 1
[All Certified Generative AI Engineer Associate Questions]

A Generative Al Engineer has developed an LLM application to answer questions about internal company policies. The Generative AI Engineer must ensure that the application doesn’t hallucinate or leak confidential data.
Which approach should NOT be used to mitigate hallucination or confidential data leakage?

  • A. Add guardrails to filter outputs from the LLM before it is shown to the user
  • B. Fine-tune the model on your data, hoping it will learn what is appropriate and not
  • C. Limit the data available based on the user’s access level
  • D. Use a strong system prompt to ensure the model aligns with your needs.
Show Suggested Answer Hide Answer
Suggested Answer: B 🗳️
by fa2bede at Nov. 26, 2024, 7:14 p.m.

Comments

Chosen Answer:
This is a voting comment (?). It is better to Upvote an existing comment if you don't have anything to add.
Switch to a voting comment New
Submit Cancel
adaine
3 days, 15 hours ago
Selected Answer: B
B is correct
upvoted 1 times
...
dementor
4 months ago
Selected Answer: B
B is the correct answer.
upvoted 2 times
...
Crunch
4 months ago
Selected Answer: B
B. Hoping for the best is not the way, the fine tuned data can still contain sensitive information
upvoted 2 times
...
fa2bede
5 months, 1 week ago
Selected Answer: C
The correct answer should be C. Limiting the data available may not help solve the hallucination problem. Fine-tuning helps reduce hallucination
upvoted 1 times
fa2bede
5 months, 1 week ago
I change my mind, B is correct. Fine tuning in this use case can be very likely increase hallucination
upvoted 1 times
...
...
Community vote distribution
A (35%)
C (25%)
B (20%)
Other
Most Voted
A voting comment increases the vote count for the chosen answer by one.

Upvoting a comment with a selected answer will also increase the vote count towards that answer by one. So if you see a comment that you already agree with, you can upvote it instead of posting a new comment.

SaveCancel
exam
Someone Bought Contributor Access for:
SY0-701
London, 1 minute ago