Unravelling Responsibility for AI (2308.02608v2)

Abstract: It is widely acknowledged that we need to establish where responsibility lies for the outputs and impacts of AI-enabled systems. But without a clear and precise understanding of what "responsibility" means, deliberations about where responsibility lies will be, at best, unfocused and incomplete and, at worst, misguided. To address this concern, this paper draws upon central distinctions in philosophy and law to clarify the concept of responsibility for AI for policymakers, practitioners, researchers and students from non-philosophical and non-legal backgrounds. Taking the three-part formulation "Actor A is responsible for Occurrence O," the paper unravels the concept of responsibility to clarify that there are different possibilities of who is responsible for AI, the senses in which they are responsible, and aspects of events they are responsible for. Criteria and conditions for fitting attributions of responsibility in the core senses (causal responsibility, role-responsibility, liability responsibility and moral responsibility) are articulated to promote an understanding of when responsibility attributions would be inappropriate or unjust. The analysis is presented with a graphical notation to facilitate informal diagrammatic reasoning and discussion about specific cases. It is illustrated by application to a scenario of a fatal collision between an autonomous AI-enabled ship and a traditional, crewed vessel at sea.