Explainable AI: current status and future directions

TL;DR

This paper reviews the current state of Explainable AI (XAI), discussing techniques across multimedia modalities, their advantages and limitations, and outlines future research directions to enhance transparency and trust in AI systems.

Contribution

It provides a comprehensive overview of XAI techniques across different media types, highlighting their strengths, weaknesses, and future research challenges.

Findings

XAI techniques vary across text, image, audio, and video modalities.

Current XAI methods have notable advantages in transparency but also face significant limitations.

Future directions include improving explanation quality and applicability across diverse AI systems.

Abstract

Explainable Artificial Intelligence (XAI) is an emerging area of research in the field of Artificial Intelligence (AI). XAI can explain how AI obtained a particular solution (e.g., classification or object detection) and can also answer other "wh" questions. This explainability is not possible in traditional AI. Explainability is essential for critical applications, such as defense, health care, law and order, and autonomous driving vehicles, etc, where the know-how is required for trust and transparency. A number of XAI techniques so far have been purposed for such applications. This paper provides an overview of these techniques from a multimedia (i.e., text, image, audio, and video) point of view. The advantages and shortcomings of these techniques have been discussed, and pointers to some future directions have also been provided.