AI RESEARCH

Quantifying Harm

arXiv CS.AI

ArXi:2209.15111v3 Announce Type: replace In earlier work we defined a qualitative notion of harm: 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. In this work, which is an expanded version of an earlier conference paper, we develop a quantitative notion of harm.