Skip to yearly menu bar Skip to main content


Poster

Reexamining the Aleatoric and Epistemic Uncertainty Dichotomy

Michael Kirchhof · Gjergji Kasneci · Enkelejda Kasneci

Hall 3 + Hall 2B #455
[ ]
Wed 23 Apr 7 p.m. PDT — 9:30 p.m. PDT

Abstract:

When discussing uncertainty estimates for the safe deployment of AI agents in the real world, the field typically distinguishes between aleatoric and epistemic uncertainty. This dichotomy may seem intuitive and well-defined at first glance, but this blog post reviews examples, quantitative findings, and theoretical arguments that reveal that popular definitions of aleatoric and epistemic uncertainties directly contradict each other and are intertwined in fine nuances. We peek beyond the epistemic and aleatoric uncertainty dichotomy and reveal a spectrum of uncertainties that help solve practical tasks especially in the age of large language models.

Live content is unavailable. Log in and register to view live content