On the Importance of Application-Grounded Experimental Design for Evaluating Explainable ML Methods. (arXiv:2206.13503v2 [cs.LG] UPDATED)

Machine Learning (ML) models now inform a wide range of human decisions, but
using ``black box'' models carries risks such as relying on spurious
correlations or errant data. To address this, researchers have proposed methods
for supplementing models with explanations of their predictions. However,
robust evaluations of these methods' usefulness in real-world contexts have
remained elusive, with experiments tending to rely on simplified settings or
proxy tasks. We present an experimental study extending a prior explainable ML
evaluation experiment and …

application arxiv design experimental importance lg ml