No invalid links evaluation metric
Last updated: Mar 04, 2025
The no invalid links metric measures whether the rows in the prediction have no invalid links.
Metric details
No invalid links is a content validation metric that uses string-based functions to analyze and validate generated LLM output text. The metric is available only when you use the Python SDK to calculate evaluation metrics.
Scope
The no invalid links metric evaluates generative AI assets only.
- Types of AI assets: Prompt templates
- Generative AI tasks:
- Text summarization
- Content generation
- Question answering
- Entity extraction
- Retrieval augmented generation (RAG)
- Supported languages: English
Scores and values
The no invalid links metric score indicates whether the rows in the prediction have no invalid links.
- Range of values: 0.0-1.0
- Ratios:
- At 0: The prediction rows do have invalid links.
- At 1: The prediction rows contain no invalid links.
Settings
- Thresholds:
- Lower limit: 0
- Upper limit: 1
Parent topic: Evaluation metrics
Was the topic helpful?
0/1000