Some Critical and Ethical Perspectives on the Empirical Turn of AI Interpretability

TL;DR

This paper critically examines how the current empirical approach to AI explanations may hinder ethical AI development, highlighting the influence of context and proposing future regulatory paths.

Contribution

It reveals that empirical explanation practices can undermine ethical AI by providing low-denunciatory explanations and emphasizes the need for external regulation or liberalization.

Findings

Empirical explanations often have low denunciatory power.

Explanation effectiveness varies with user context such as gender and education.

Liberal explanation practices may hinder ethical AI development.

Abstract

We consider two fundamental and related issues currently faced by Artificial Intelligence (AI) development: the lack of ethics and interpretability of AI decisions. Can interpretable AI decisions help to address ethics in AI? Using a randomized study, we experimentally show that the empirical and liberal turn of the production of explanations tends to select AI explanations with a low denunciatory power. Under certain conditions, interpretability tools are therefore not means but, paradoxically, obstacles to the production of ethical AI since they can give the illusion of being sensitive to ethical incidents. We also show that the denunciatory power of AI explanations is highly dependent on the context in which the explanation takes place, such as the gender or education level of the person to whom the explication is intended for. AI ethics tools are therefore sometimes too flexible and self-regulation through the liberal production of explanations do not seem to be enough to address ethical issues. We then propose two scenarios for the future development of ethical AI: more external regulation or more liberalization of AI explanations. These two opposite paths will play a major role on the future development of ethical AI.