To trust or not to trust an explanation: using LEAF to evaluate local linear XAI methods

TL;DR

This paper introduces LEAF, a Python framework for standardized, unbiased evaluation of local linear explanation methods like LIME and SHAP, addressing their current shortcomings and promoting better XAI practices.

Contribution

The paper defines a comprehensive set of metrics for evaluating local linear explanations and implements them in LEAF, facilitating improved assessment and development of XAI methods.

Findings

LIME and SHAP explanations often exhibit instability and divergence from theoretical properties.

Current evaluation practices for local explanations are inconsistent and biased.

LEAF provides a standardized framework to improve explanation assessment.

Abstract

The main objective of eXplainable Artificial Intelligence (XAI) is to provide effective explanations for black-box classifiers. The existing literature lists many desirable properties for explanations to be useful, but there is no consensus on how to quantitatively evaluate explanations in practice. Moreover, explanations are typically used only to inspect black-box models, and the proactive use of explanations as a decision support is generally overlooked. Among the many approaches to XAI, a widely adopted paradigm is Local Linear Explanations - with LIME and SHAP emerging as state-of-the-art methods. We show that these methods are plagued by many defects including unstable explanations, divergence of actual implementations from the promised theoretical properties, and explanations for the wrong label. This highlights the need to have standard and unbiased evaluation procedures for Local Linear Explanations in the XAI field. In this paper we address the problem of identifying a clear and unambiguous set of metrics for the evaluation of Local Linear Explanations. This set includes both existing and novel metrics defined specifically for this class of explanations. All metrics have been included in an open Python framework, named LEAF. The purpose of LEAF is to provide a reference for end users to evaluate explanations in a standardised and unbiased way, and to guide researchers towards developing improved explainable techniques.