Skip to main content

Create a RAG Hallucination Policy

Select a Policy Type​

After selecting "Hallucination Policy", choose what subtype of hallucination policy you'd like to create.

Hallucination Policy Setup

Select a Moderation Behavior​

Next, determine which moderation behavior your policy should follow. Hallucination policies support Flag and Block behaviors.

Select Policy Usage​

Hallucination policies can only be applied to model outputs.

Provide Policy Information​

Provide a policy name and description, these will only be used for identification in the future. In this step, you can also set a threshold score for each RAG hallucination metric: retrieval relevance, response faithfulness, and response relevance. Model responses with a score greater than this threshold will be considered violations.

Hallucination Policy Setup

Create your Policy​

After the policy is created, it will appear in the policy dashboard.