AIAI Seminar-Friday 3rd October 2025 by Visiting Speaker: Marija Slavkovik

Title: Aggregation problems in Machine Ethics and Value Alignment

Abstract: Artificial agents increasingly make decisions with farreaching consequences. It is therefore imperative to ensure that their actions are not only functionally effective but also normatively appropriate. Two major paradigms address this challenge: machine ethics and value alignment. But who gets to say what the right thing for a machine to do is? Some have argued that this question should be solved by some form of aggregation. Machine ethics typically engages in moral aggregation, especially through value and (descriptive) uncertainty aggregation. Value alignment approaches tend to rely on social aggregation to manage value pluralism and moral uncertainty, often implicitly or indirectly. This talk is based on a recently accepted paper to the AIES.org conference. The talk disentangles the forms of aggregation and analyzes their roles across three stages of machine moral reasoning: moral evaluation, moral assessment, and moral decision. 

Bio: Marija Slavkovik is a Professor with the Faculty for Social Sciences of the University of Bergen. Her background is in computer science and artificial intelligence. She received her PhD from the University of Luxembourg in Multi-agent systems and computational social choice. She has been doing research in machine ethics since 2012. Machine ethics studies how moral reasoning can or should be automated.  Marija works on formalising ethical collective decision-making.   Somewhat badly maintained personal webpage, which she promises to update, can be found here https://slavkovik.com/