The Gradient: Perspectives on AI cover image

Upol Ehsan on Human-Centered Explainable AI and Social Transparency

The Gradient: Perspectives on AI

00:00

Expanding Explainability Towards Social Transparency in AI Systems

The paper expands our conception on explainable AI beyond the realms of algorithmic transparency by doing what? By adding this new concept called social transparency, which is actually not like new new in the sense that we created it in the context of XAI. So for the longest time, I've been arguing that we need to look outside the box for XAI for XAI. But how can you get the explainability of this assemblage, this two part system, the human and the AI, by just focusing on the AI? That's the question that it's asking."

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app