Towards Formal Definitions of Blameworthiness, Intention, and Moral Responsibility
This work addresses the challenge of formalizing moral concepts for researchers in AI ethics and philosophy, though it appears incremental as it builds on existing definitions of causality.
The paper tackles the problem of formalizing blameworthiness and intention by providing definitions relative to an epistemic state, which are then used to inform moral responsibility judgments. The result is that these definitions offer insight into commonsense intuitions across various puzzling cases from existing literature.
We provide formal definitions of degree of blameworthiness and intention relative to an epistemic state (a probability over causal models and a utility function on outcomes). These, together with a definition of actual causality, provide the key ingredients for moral responsibility judgments. We show that these definitions give insight into commonsense intuitions in a variety of puzzling cases from the literature.