Readability evaluation metric

The readability metric determines how difficult the model's output is to read by measuring characteristics such as sentence length and word complexity.

Metric details

Readability is a generative AI quality evaluation metric that measures how well generative AI assets perform tasks.

Scope

The readability metric evaluates generative AI assets only.

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

Scores and values

The readability metric score indicates how easy the model's output is to read. Higher scores indicate that the model's output is easier to read.

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

Settings

  • Thresholds:
    • Lower limit: 60

Parent topic: Evaluation metrics