A Formalization of Kant's Second Formulation of the Categorical Imperative
This work addresses the challenge of computational ethics for AI systems by formalizing a key philosophical principle, but it is incremental as it builds on existing ethical formalizations without broad application or SOTA impact.
The researchers tackled the problem of formalizing Kant's second formulation of the categorical imperative, an ethical principle requiring agents to treat persons as ends, by developing Kantian causal agency models to represent moral patients, actions, and causal influence, and they formalized strict and wide duty versions, though they noted limitations in handling certain Kantian cases.
We present a formalization and computational implementation of the second formulation of Kant's categorical imperative. This ethical principle requires an agent to never treat someone merely as a means but always also as an end. Here we interpret this principle in terms of how persons are causally affected by actions. We introduce Kantian causal agency models in which moral patients, actions, goals, and causal influence are represented, and we show how to formalize several readings of Kant's categorical imperative that correspond to Kant's concept of strict and wide duties towards oneself and others. Stricter versions handle cases where an action directly causally affects oneself or others, whereas the wide version maximizes the number of persons being treated as an end. We discuss limitations of our formalization by pointing to one of Kant's cases that the machinery cannot handle in a satisfying way.