4 papers
What UI Design Can Do For "Good" Oversight Work: A Three-Month Action Research Study
Cedric Faas, Lisa Dargasz, Julius Gabelmann +4
With AI automating consequential tasks, human oversight is required for ethical, legal, and practical reasons. Yet these oversight tasks can be demanding and often make for poor wo…
Breaking Up with Normatively Monolithic Agency with GRACE: A Reason-Based Neuro-Symbolic Architecture for Safe and Ethical AI Alignment
Felix Jahn, Yannic Muskalla, Lisa Dargasz +2
As AI agents become increasingly autonomous, widely deployed in consequential contexts, and efficacious in bringing about real-world impacts, ensuring that their decisions are not…
Integrating Reason-Based Moral Decision-Making in the Reinforcement Learning Architecture
Lisa Dargasz
Reinforcement Learning is a machine learning methodology that has demonstrated strong performance across a variety of tasks. In particular, it plays a central role in the developme…
Acting for the Right Reasons: Creating Reason-Sensitive Artificial Moral Agents
Kevin Baum, Lisa Dargasz, Felix Jahn +2
We propose an extension of the reinforcement learning architecture that enables moral decision-making of reinforcement learning agents based on normative reasons. Central to this a…