Ошибка калибровки

AbstractPre-trained Transformers are now ubiquitous in natural language processing, but despite their high end-task performance, little is known empirically about whether they are calibrated. Specifically, do these models’ posterior probabilities …...

AbstractWe investigate model calibration in the setting of zero-shot cross-lingual transfer with large-scale pre-trained language models. The level of model calibration is an important metric for evaluating the trustworthiness of …...

AbstractModern NLP classifiers are known to return uncalibrated estimations of class posteriors. Existing methods for posterior calibration rescale the predicted probabilities but often have an adverse impact on final classification …...