Databricks Certified Generative AI Engineer Associate — Question 80

A Generative AI Engineer is building a system that will answer questions on currently unfolding news topics. As such, it pulls information from a variety of sources including articles and social media posts. They are concerned about toxic posts on social media causing toxic outputs from their system.

Which guardrail will limit toxic outputs?

Answer options

• A. Reduce the amount of context items the system will include in consideration for its response.
• B. Use only approved social media and news accounts to prevent unexpected toxic data from getting to the LLM.
• C. Log all LLM system responses and perform a batch toxicity analysis monthly.
• D. Implement rate limiting.

Correct answer: B

Explanation

Option B is correct because using only approved social media and news accounts helps ensure that the data fed into the system is reliable and free of toxic content. The other options, while potentially useful in their own right, do not directly address the issue of controlling the quality of the input data, which is crucial for preventing toxic outputs.