A Comparative Study of Faithfulness Metrics for Model Interpretability Methods. (arXiv:2204.05514v1 [cs.CL])

Interpretation methods to reveal the internal reasoning processes behind
machine learning models have attracted increasing attention in recent years. To
quantify the extent to which the identified interpretations truly reflect the
intrinsic decision-making mechanisms, various faithfulness evaluation metrics
have been proposed. However, we find that different faithfulness metrics show
conflicting preferences when comparing different interpretations. Motivated by
this observation, we aim to conduct a comprehensive and comparative study of
the widely adopted faithfulness metrics. In particular, we introduce two
assessment …

arxiv interpretability metrics model interpretability study