The normalized discounted cumulative gain metric measures the ranking quality of the retrieved contexts.
Metric details
Normalized discounted cumulative gain is a retrieval quality metric for generative AI quality evaluations that measures the quality of how a retrieval system ranks relevant contexts. Retrieval quality metrics are calculated with LLM-as-a-judge models.
Scope
The normalized discounted cumulative gain metric evaluates generative AI assets only.
- Types of AI assets: Prompt templates
- Generative AI tasks: Retrieval Augmented Generation (RAG)
- Supported languages: English
Scores and values
The normalized discounted cumulative gain metric score indicates how accurately the retrieved contexts are ranked. Higher scores indicate that the ranking of retrieved contexts is correct. Lower scores indicate that the ranking of retrieved contexts is incorrect.
- Range of values: 0.0-1.0
- Best possible score: 1.0
- Ratios:
- At 1: The retrieved contexts are ranked in the correct order.
Settings
- Thresholds:
- Lower bound: 0
- Upper bound: 1
Parent topic: Evaluation metrics