Is Task-Agnostic Explainable AI a Myth?

TL;DR

This paper critically examines the limitations of current explainable AI methods across different data types, emphasizing the need for a conceptual breakthrough to achieve truly task-agnostic explanations.

Contribution

It provides a unified framework highlighting common challenges and limitations in contemporary XAI methods across multiple data modalities.

Findings

XAI methods often become black boxes themselves.

Persistent challenges hinder task-agnostic explainability.

A conceptual breakthrough is needed for effective XAI.

Abstract

Our work serves as a framework for unifying the challenges of contemporary explainable AI (XAI). We demonstrate that while XAI methods provide supplementary and potentially useful output for machine learning models, researchers and decision-makers should be mindful of their conceptual and technical limitations, which frequently result in these methods themselves becoming black boxes. We examine three XAI research avenues spanning image, textual, and graph data, covering saliency, attention, and graph-type explainers. Despite the varying contexts and timeframes of the mentioned cases, the same persistent roadblocks emerge, highlighting the need for a conceptual breakthrough in the field to address the challenge of compatibility between XAI methods and application tasks.