Post hoc models are becoming popular as additional tools to evaluate the results of black-box models and to provide explanations of the predictions they give. In this paper the main concerns that Local Induced models raise in the pointwise explanation of heavily overparametrized black-box models are discussed in depth, highlighting some vulnerabilities, some underrated issues and giving some warnings on the potentially negative effect on user trust of this explainability framework
Pitfalls of local explainability in complex black-box models
Maratea
;A. Ferone
2021-01-01
Abstract
Post hoc models are becoming popular as additional tools to evaluate the results of black-box models and to provide explanations of the predictions they give. In this paper the main concerns that Local Induced models raise in the pointwise explanation of heavily overparametrized black-box models are discussed in depth, highlighting some vulnerabilities, some underrated issues and giving some warnings on the potentially negative effect on user trust of this explainability frameworkFile in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.