META-EVALUATING STABILITY MEASURES: MAX-SENSTIVITY & AVG-SENSITIVITY

作     者：Miró-Nicolau, Miquel Jaume-I-Capó, Antoni Moyà-Alcover, Gabriel 

作者机构： University of the Balearic Islands Dpt. of Mathematics and Computer Science Palma07122 Spain 

出 版 物：《arXiv》 (arXiv)

年 卷 期：2024年

核心收录：

主　　题：Decision trees 

摘      要：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. © 2024, CC BY.