A Perspective on Explainable Artificial Intelligence Methods: SHAP and LIME

Salih, Ahmed; Raisi‐Estabragh, Zahra; Galazzo, Ilaria Boscolo; Radeva, Petia; Petersen, Steffen E.; Lekadir, Karim; Menegaz, Gloria

doi:10.1002/aisy.202400304

articleAdvanced Intelligent SystemsJun 27, 2024GOLD OA

A Perspective on Explainable Artificial Intelligence Methods: SHAP and LIME

ASAhmed Salih ZRZahra Raisi‐Estabragh IBIlaria Boscolo Galazzo PRPetia Radeva SESteffen E. Petersen

St Bartholomew's Hospital · University of Leicester · +9 more institutions

Indexed incrossrefdoaj

Abstract

EXplainable artificial intelligence (XAI) methods have emerged to convert the black box of machine learning (ML) models into a more digestible form. These methods help to communicate how the model works with the aim of making ML models more transparent and increasing the trust of end‐users in their output. SHapley Additive exPlanations (SHAP) and Local Interpretable Model Agnostic Explanation (LIME) are two widely used XAI methods, particularly with tabular data. In this perspective piece, the way the explainability metrics of these two methods are generated is discussed and a framework for the interpretation of their outputs, highlighting their weaknesses and strengths is proposed. Specifically, their…

Citation impact

594

total citations

FWCI: 185.84
Percentile: 100%
References: 25

Citations per year

Authors

7

Topics & keywords

Topics

Keywords

Collinearity
Perspective (graphical)
Interpretation (philosophy)
Computer science
Artificial intelligence
Dependency (UML)
Strengths and weaknesses
Lime

No related works found for this paper.