AI RESEARCH
Evaluating Local Explainability Metrics for Machine Learning Models on Tabular Data
arXiv CS.LG
•
ArXi:2605.27618v1 Announce Type: new Despite the wide use of explainability techniques to attempt to understand the behavior of Artificial Intelligence (AI), the generated explanations may not always be reliable. An explanation can appear plausible to humans but fail to capture the internal reasoning of a model, particularly when dealing with complex tabular data.