Learning Tractable Probabilistic Models for Moral Responsibility and Blame

Lewis Hammond, Vaishak Belle

Research output: Contribution to journalArticlepeer-review


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 rulebased 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.
Original languageEnglish
Pages (from-to)621-659
Number of pages39
JournalData Mining and Knowledge Discovery
Issue number2
Early online date25 Jan 2021
Publication statusPublished - 1 Mar 2021


  • Tractable probabilistic models
  • Learning for ethical reasoning


Dive into the research topics of 'Learning Tractable Probabilistic Models for Moral Responsibility and Blame'. Together they form a unique fingerprint.

Cite this