Meta-evaluating stability measures: MAX-Senstivity & AVG-Sensitivity
This work addresses the challenge of ensuring robust and stable XAI systems for researchers and practitioners, but it is incremental as it focuses on meta-evaluating existing measures rather than introducing new ones.
The authors tackled the problem of evaluating the reliability of stability measures in eXplainable AI (XAI) by proposing a novel meta-evaluation approach, which revealed that AVG-Sensitivity and MAX-Sensitivity metrics failed to identify random explanations as erroneous, indicating their unreliability.
The use of eXplainable Artificial Intelligence (XAI) systems has introduced a set of challenges that need resolution. The XAI robustness, or stability, has been one of the goals of the community from its beginning. Multiple authors have proposed evaluating this feature using objective evaluation measures. Nonetheless, many questions remain. With this work, we propose a novel approach to meta-evaluate these metrics, i.e. analyze the correctness of the evaluators. We propose two new tests that allowed us to evaluate two different stability measures: AVG-Sensitiviy and MAX-Senstivity. We tested their reliability in the presence of perfect and robust explanations, generated with a Decision Tree; as well as completely random explanations and prediction. The metrics results showed their incapacity of identify as erroneous the random explanations, highlighting their overall unreliability.