These tools and metrics are designed to help AI actors develop and use trustworthy AI systems and applications that respect human rights and are fair, transparent, explainable, robust, secure and safe.
FrugalScore
FrugalScore is a reference-based metric for Natural Language Generation (NLG) model evaluation. It is based on a distillation approach that allows to learn a fixed, low cost version of any expensive NLG metric, while retaining most of its original performance.
The FrugalScore models are obtained by continuing the pretraining of small models on a synthetic dataset constructed using summarization, backtranslation and denoising models. During the training, the small models learn the internal mapping of the expensive metric, including any similarity function.
About the metric
You can click on the links to see the associated metrics
Objective(s):
Purpose(s):
Lifecycle stage(s):
Target users:
