AI RESEARCH
Regional Explanations: Bridging Local and Global Variable Importance
arXiv CS.AI
•
ArXi:2604.11223v1 Announce Type: cross We analyze two widely used local attribution methods, Local Shapley Values and LIME, which aim to quantify the contribution of a feature value $x_i$ to a specific prediction $f(x_1, \dots, x_p)$. Despite their widespread use, we identify fundamental limitations in their ability to reliably detect locally important features, even under ideal conditions with exact computations and independent features.