Skip to main content

Create a RAG Hallucination - Input Relevance Policy

RAG Hallucination - Input Relevance policies can be used to detect if an input is relevant to the retrieved contexts. See the Hallucination Policies page in Key Concepts for more details on the RAG Hallucination policies.

1. Select Policy Type​

After selecting the Hallucination Detection policy option, select the Input Relevance policy subtype.

2. Select a Moderation Behavior​

Choose the moderation behavior for your policy. RAG Hallucination policies support two behaviors:

  • Flag: Flag content for moderator review
  • Block: Block model outputs containing hallucinated content

Hallucination Setup

3. Provide Policy Details​

Provide a policy title, this will be used for identification in the future. In this step, you can also set a threshold score. For the input policy, the score indates the relevance of the user input to the retrieved context.A higher score indicates a more relevant input. Scores lower than the thresholds are considered irrelevant or hallucinations.

Hallcuination Setup

4. Finalize and Create your Policy​

Once you’ve completed the setup, click Create Policy. The newly created policy will appear in your Policy Dashboard, where you can manage and track all your policies.