To prevent an Azure OpenAI model (such as GPT-4 or GPT-3.5) from returning outputs that include hate speech, you must configure Azure AI Content Safety content filters on the model deployment. Content filters evaluate prompts and/or completions for categories like Hate/Unfairness, Harassment/Violence, Sexual, and Self-harm and can block or redact responses when they exceed your selected threshold. Applying a content filter to Model1 ensures that App1 will not return hate speech, satisfying the requirement.
Why the other options are incorrect:
* A. Frequency penalty - discourages token/repetition in output; it does not moderate harmful content.
* B. Abuse monitoring - provides telemetry/policy monitoring for potential misuse; it is not a response- time content filter and does not block specific hate content.
* D. Temperature - adjusts randomness/creativity; it does not enforce safety.
Microsoft Azure AI References
* Azure OpenAI Service - Safety system & content filtering (configure per deployment; categories include Hate).
* Azure AI Content Safety - Overview and moderation categories.
* Azure OpenAI Studio - Attach Content Safety filters to deployments (prompt/completion filtering).