Numerator: claims supported by the retrieved context

The passage around this formula

Ragas is a widely used reference-free evaluation framework built explicitly around this separation: it scores retrieval effectiveness, the faithfulness with which a model uses retrieved passages, and generation quality, without requiring a human-written ground-truth answer for every query [ 4 ] . Its faithfulness metric is defined mechanically rather than as a vague notion of “sounding grounded”: a response is decomposed into individual factual claims, each claim is checked against the retrieved context to see whether it can be inferred from it, and the score is the resulting ratio, as the framework’s own documentation states [ 5 ] : $\mathrm{Faithfulness} = \frac{\text{claims supported by the retrieved context}}{\text{total claims in the response}}$. Notice what this formula does and…

Read this part in the article →