EXIST-2024: Sexism identification in tweets (soft-soft)

This is a binary classification task where the goal is to decide whether a given tweet contains sexist expressions or behaviors (i.e., it is sexist in itself, describes a sexist situation, or criticizes sexist behavior). This task includes a soft-soft evaluation, where the predicted label probabilities are compared with the probabilities defined based on the disagreement in the annotation within the gold standard.