Interpretation drift in explainable AI under label noise

Abstract The comprehensibility and human interpretation of classification models are crucial in many applications, such as decision support systems and knowledge discovery, where explanations drive action. However, the presence of class label noise, widespread in real-life data, can significantly im...

Descripció completa

Dades bibliogràfiques

Autors principals:	Alisa Raikovskaia, Nurlan Rakhimzhanov, Oleg S. Pianykh
Format:	Artigo
Idioma:	Inglês
Publicat:	Nature Portfolio 2026-03-01
Col·lecció:	Scientific Reports
Matèries:	Explainable/interpretable AI Rule learning Boolean conjunctions Interpretation fragility
Accés en línia:	https://doi.org/10.1038/s41598-026-37070-4
Etiquetes:	Afegir etiqueta Sense etiquetes, Sigues el primer a etiquetar aquest registre!