Câu 35: Databricks Certified Generative AI Engineer Associate
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?
Nội dung câu hỏi
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?
Các lựa chọn
Đáp án được giữ gọn theo nhãn A, B, C, D trong phần bình chọn tương tác.
- 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 — đáp án hiện tại
- 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.
Cộng đồng
0 bình luận công khai. Tên thành viên được ẩn một phần.
Chưa có bình luận. Mở giao diện tương tác để bắt đầu thảo luận.