English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

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

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