Even if Explanations: Prior Work, Desiderata & Benchmarks for Semi-Factual XAI

TL;DR

This paper surveys semi-factual explanations in XAI, highlighting their history, defining key desiderata, and benchmarking algorithms to guide future research in this less-explored area.

Contribution

It introduces a comprehensive overview of semi-factual XAI, establishes desiderata, and provides benchmark evaluations including a novel naive method.

Findings

Benchmark tests of historical algorithms

Introduction of a naive baseline method

Identification of key desiderata for semi-factual XAI

Abstract

Recently, eXplainable AI (XAI) research has focused on counterfactual explanations as post-hoc justifications for AI-system decisions (e.g. a customer refused a loan might be told: If you asked for a loan with a shorter term, it would have been approved). Counterfactuals explain what changes to the input-features of an AI system change the output-decision. However, there is a sub-type of counterfactual, semi-factuals, that have received less attention in AI (though the Cognitive Sciences have studied them extensively). This paper surveys these literatures to summarise historical and recent breakthroughs in this area. It defines key desiderata for semi-factual XAI and reports benchmark tests of historical algorithms (along with a novel, naieve method) to provide a solid basis for future algorithmic developments.