Is Task-Agnostic Explainable AI a Myth?
This work addresses the problem of unreliable XAI methods for researchers and decision-makers, but it is incremental as it synthesizes existing challenges without proposing a new solution.
The paper tackles the challenge of unifying explainable AI (XAI) methods across different data types, demonstrating that current approaches often become black boxes themselves and highlighting persistent roadblocks that require a conceptual breakthrough for better task compatibility.
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.