Learning Tractable Probabilistic Models for Moral Responsibility and Blame

TL;DR

This paper introduces a hybrid learning framework for automatically modeling moral responsibility and blameworthiness from data, enabling efficient reasoning in autonomous systems for critical decision-making scenarios.

Contribution

It presents a novel hybrid approach combining data-driven and rule-based methods to learn models of moral responsibility and blameworthiness for autonomous systems.

Findings

System effectively models moral scenarios from data

Achieves tractable reasoning for responsibility judgments

Outperforms human judgment in illustrative domains

Abstract

Moral responsibility is a major concern in autonomous systems, with applications ranging from self-driving cars to kidney exchanges. Although there have been recent attempts to formalise responsibility and blame, among similar notions, the problem of learning within these formalisms has been unaddressed. From the viewpoint of such systems, the urgent questions are: (a) How can models of moral scenarios and blameworthiness be extracted and learnt automatically from data? (b) How can judgements be computed effectively and efficiently, given the split-second decision points faced by some systems? By building on constrained tractable probabilistic learning, we propose and implement a hybrid (between data-driven and rule-based methods) learning framework for inducing models of such scenarios automatically from data and reasoning tractably from them. We report on experiments that compare our system with human judgement in three illustrative domains: lung cancer staging, teamwork management, and trolley problems.