ferret.TauLOO_Evaluation#
- class ferret.TauLOO_Evaluation(model, tokenizer, task_name)[source]#
- __init__(model, tokenizer, task_name)#
Methods
__init__
(model, tokenizer, task_name)compute_evaluation
(explanation, ...)Evaluate an explanation on the tau-LOO metric, i.e., the Kendall tau correlation between the explanation scores and leave one out (LOO) scores, computed by leaving one feature out and computing the change in the prediciton probability
Attributes
BEST_VALUE
LOWER_IS_BETTER
MAX_VALUE
METRIC_FAMILY
MIN_VALUE
NAME
SHORT_NAME
tokenizer