Skip to main content

Create a Hallucination Policy - Summarization Consistency

The Response summarization Consistency Policy detects if the model’s response summaries are consistent with user-provided source text in the prompt input. See the Hallucination Policies page in Key Concepts for more details on the Summarization Consistency policy.

1. Select Policy Type​

After selecting the Hallucination Detection policy option, select the Response Summarization Consistency policy subtype.

2. Select a Moderation Behavior​

Choose the moderation behavior for your policy. Summarization consistency 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 which will be used for identification in the future. In this step, you can also set a hallucination threshold score. For summarization consistency policies, the score indicates the probability that the response is consistent with the input. As a result, scores higher than the threshold are compliant.

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.