DatabricksDatabricks
GENERATIVE-AI-ENGINEER-ASSOCIATE · Question #44
GENERATIVE-AI-ENGINEER-ASSOCIATE Question #44: Real Exam Question with Answer & Explanation
The correct answer is B: Fine-tune the model on your data, hoping it will learn what is appropriate and not. See the full explanation below for the reasoning.
LLM Security and Safety
Question
A Generative AI 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?
Options
- AAdd guardrails to filter outputs from the LLM before it is shown to the user
- BFine-tune the model on your data, hoping it will learn what is appropriate and not
- CLimit the data available based on the user's access level
- DUse a strong system prompt to ensure the model aligns with your needs.
Topics
#LLM Safety#Data Leakage Prevention#Hallucination Mitigation#Fine-tuning
Community Discussion
No community discussion yet for this question.