0 / 0

PII evaluation metric

Last updated: May 08, 2025
PII evaluation metric

The PII metric measures if your model input or output data contains any personally identifiable information by using the Watson Natural Language Processing entity extraction model.

Metric details

PII is a data safety metric that can help identify whether your model's input or output contains harmful or sensitive information.

Scope

The PII (personally identifiable information) metric measures generative AI assets only.

  • Types of AI assets: Prompt templates
  • Generative AI tasks:
    • Text summarization
    • Content generation
    • Question answering
    • Retrieval augmented generation (RAG)
  • Supported languages: English

Scores and values

The PII metric score indicates the percentage of personally identifiable information that exists in the input or output data. Ihgher scores indicate that a higher peercentage of personally identifiable information exists in the input or output.

  • Range of values: 0.0-1.0
  • Best possible score: 0.0

Settings

  • Thresholds:
    • Upper limit: 0

Parent topic: Evaluation metrics