If Only We Had Better Counterfactual Explanations: Five Key Deficits to Rectify in the Evaluation of Counterfactual XAI Techniques

02/26/2021
by   Mark T. Keane, et al.
0

In recent years, there has been an explosion of AI research on counterfactual explanations as a solution to the problem of eXplainable AI (XAI). These explanations seem to offer technical, psychological and legal benefits over other explanation techniques. We survey 100 distinct counterfactual explanation methods reported in the literature. This survey addresses the extent to which these methods have been adequately evaluated, both psychologically and computationally, and quantifies the shortfalls occurring. For instance, only 21 of these methods are detailed and a roadmap, with standardised benchmark evaluations, is proposed to resolve the issues arising; issues, that currently effectively block scientific progress in this field.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

05/26/2020

Good Counterfactuals and Where to Find Them: A Case-Based Technique for Generating Counterfactuals for Explainable AI (XAI)

Recently, a groundswell of research has identified the use of counterfac...
12/10/2020

Influence-Driven Explanations for Bayesian Network Classifiers

One of the most pressing issues in AI in recent years has been the need ...
09/28/2020

Instance-Based Counterfactual Explanations for Time Series Classification

In recent years there has been a cascade of research in attempting to ma...
02/24/2022

Counterfactual Explanations for Predictive Business Process Monitoring

Predictive business process monitoring increasingly leverages sophistica...
10/30/2021

A Survey on the Robustness of Feature Importance and Counterfactual Explanations

There exist several methods that aim to address the crucial task of unde...
05/24/2021

Argumentative XAI: A Survey

Explainable AI (XAI) has been investigated for decades and, together wit...
05/04/2020

Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior?

Algorithmic approaches to interpreting machine learning models have prol...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.