Benjamin Krarup

Papers

Total Citations

H-Index

About

Benjamin Krarup is a researcher at the forefront of ethical AI and robotics, specializing in the development of transparent, morally-aware decision-making systems. His work centers on creating frameworks that allow autonomous agents to not only make ethically sound choices but also explain their reasoning in human-understandable terms. Krarup’s most notable contribution is his pioneering paper, "Towards Contrastive Explanations for Comparing the Ethics of Plans" (2020), which has garnered 5 citations and laid critical groundwork for explainable AI in high-stakes environments. This research addresses the pressing need for AI systems—increasingly trusted with life-altering decisions—to provide clear, comparative justifications for their ethical judgments. By focusing on contrastive explanations, Krarup enables users to understand why one plan was chosen over another, bridging the gap between complex algorithmic ethics and practical human oversight. His work is instrumental in building public trust and ensuring accountability in autonomous systems, from healthcare to autonomous vehicles. Krarup’s research continues to shape the responsible development of AI, making him a key voice in the ethical deployment of intelligent agents.