Articles  |    |  July 1, 2006

Computational Models of Ethical Reasoning: Challenges, Initial Steps, and Future Directions

Article by Bruce McLaren.
Published in IEEE Intelligent Systems.


This article reviews progress in developing computational models of ethical reasoning, looks in detail at two seminal machine ethics systems— Truth-Teller and SIROCCO—and discusses promising future directions.

How can machines support or, even more significantly, replace humans in performing ethical reasoning? This question greatly interests machine ethics researchers.Imbuing a computer with the ability to reason about ethical problems and dilemmas is as difficult a task as there is for AI scientists and engineers. First, ethical reasoning is based on abstract principles that you can’t easily apply in a formal, deductive fashion. So, the favorite tools of logicians and mathematicians, such as first order logic, aren’t applicable. Second, throughout intellectual history, philosophers have proposed many theoretical frameworks, such as Aristotelian virtue theory, the ethics of respect for persons, act utilitarianism, utilitarianism, and prima facie duties, and no universal agreement exists on which ethical theory or approach is the best. Furthermore, any of these theories or approaches could be the focus of inquiry, but all are difficult to make computational without relying on simplifying assumptions and subjective interpretation. Finally, ethical issues touch human beings profoundly and fundamentally. The premises, beliefs, and principles that humans use to make ethical decisions are quite varied, not fully understood, and often inextricably intertwined with religious beliefs.

How do you take such uniquely human characteristics and distill them into a computer program? Undaunted by the challenge, scientists and engineers have, over the past 15 years, developed several computer programs that take initial steps in addressing these difficult problems. Here, I briefly describe a few of these programs and discuss in detail two programs that I developed, both of which employ techniques from the area of AI known as case-based reasoning and implement aspects of the ethical approach known as casuistry. One of these programs, TruthTeller, accepts a pair of ethical dilemmas and describes the salient similarities and differences between them, from both an ethical and a pragmatic perspective. The other program, SIROCCO, accepts a single ethical dilemma and retrieves other cases and ethical principles that might be relevant. [ . . . ]

About the Author

Bruce McLaren is an American researcher, academic and author. He is an Associate Research Professor at Carnegie Mellon University and a former President of the International Artificial Intelligence in Education Society (2017-2019).