SARI evaluation metric

The SARI metric compares the predicted sentence output against the reference sentence output to measure the quality of words that the model uses to generate sentences.

Metric details

SARI (system output against references and against the input sentence) is a generative AI quality evaluation metric that measures how well generative AI assets perform tasks.

Scope

The SARI metric evaluates generative AI assets only.

  • Types of AI assets: Prompt templates
  • Generative AI tasks: Text summarization
  • Supported languages: English

Scores and values

The SARI metric score indicates the quality of words that are used to generate sentences. Higher scores indicate a higher quality of words are used to generate sentences.

Settings

  • Thresholds:
    • Lower limit: 0
    • Upper limit: 100

Parent topic: Evaluation metrics