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...

Fuld beskrivelse

Bibliografiske detaljer

Principais autores:	Alisa Raikovskaia, Nurlan Rakhimzhanov, Oleg S. Pianykh
Format:	Artigo
Sprog:	Inglês
Udgivet:	Nature Portfolio 2026-03-01
Serier:	Scientific Reports
Fag:	Explainable/interpretable AI Rule learning Boolean conjunctions Interpretation fragility
Online adgang:	https://doi.org/10.1038/s41598-026-37070-4
Tags:	Tilføj Tag Ingen Tags, Vær først til at tagge denne postø!