Quantifying Harm

Sander Beckers, Hana Chockler, Joseph Y. Halpern

Research output: Chapter in Book/Report/Conference proceedingConference paperpeer-review

55 Downloads (Pure)

Abstract

In [Beckers et. al. 2022] a qualitative notion of harm is defined: either harm is caused, or it is not. For practical applications, we often need to quantify harm; for example, we may want to choose the least harmful of a set of possible interventions. We first present a quantitative definition of harm in a deterministic context involving a single individual, then we consider the issues involved in dealing with uncertainty regarding the context and going from a notion of harm for a single individual to a notion of ``societal harm'', which involves aggregating the harm to individuals. We show that the ``obvious'' way of doing this (just taking the expected harm for an individual and then summing the expected harm over all individuals) can lead to counterintuitive or inappropriate answers, and discuss alternatives, drawing on work from the decision-theory literature.
Original languageEnglish
Title of host publicationTHE 32nd INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE (IJCAI), 2023
Publication statusAccepted/In press - 2023

Fingerprint

Dive into the research topics of 'Quantifying Harm'. Together they form a unique fingerprint.

Cite this