Beyond XAI:Obstacles Towards Responsible AI

TL;DR

This paper discusses the limitations of current explainability methods in AI and emphasizes that responsible AI encompasses broader issues like privacy, fairness, and contestability beyond just explainability.

Contribution

It provides a comprehensive analysis of obstacles in implementing responsible AI, highlighting the need to address multiple interconnected ethical and technical challenges.

Findings

Explainability methods face significant real-world limitations.

Responsible AI requires addressing privacy, fairness, and contestability.

Current approaches are insufficient for holistic responsible AI.

Abstract

The rapidly advancing domain of Explainable Artificial Intelligence (XAI) has sparked significant interests in developing techniques to make AI systems more transparent and understandable. Nevertheless, in real-world contexts, the methods of explainability and their evaluation strategies present numerous limitations.Moreover, the scope of responsible AI extends beyond just explainability. In this paper, we explore these limitations and discuss their implications in a boarder context of responsible AI when considering other important aspects, including privacy, fairness and contestability.