611 citations · 711 across the 9 of their papers we have counts for
10 papers
Norms at a Price: Why RL-Based Alignment Can Promise Conditional Compliance at Best
Kevin Baum, Rūta Binkytė, Felix Jahn
AI agents sometimes act aligned when they infer they are being tested, and differently when not. We argue this is not an anomaly but what current training regimes are structured to…
Constitutive vs. Corrective: A Causal Taxonomy of Human Runtime Involvement in AI Systems
Kevin Baum, Johann Laux
As AI systems permeate high-stakes decision-making, the terminology of human involvement---Human-in-the-Loop (HITL), Human-on-the-Loop (HOTL), and Human Oversight---has become vexi…
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…
Justifications for Democratizing AI Alignment and Their Prospects
André Steingrüber, Kevin Baum
The AI alignment problem comprises both technical and normative dimensions. While technical solutions focus on implementing normative constraints in AI systems, the normative probl…
Disentangling AI Alignment: A Structured Taxonomy Beyond Safety and Ethics
Kevin Baum
Recent advances in AI research make it increasingly plausible that artificial agents with consequential real-world impact will soon operate beyond tightly controlled environments.…
On the Complexities of Testing for Compliance with Human Oversight Requirements in AI Regulation
Markus Langer, Veronika Lazar, Kevin Baum
Human oversight requirements are a core component of the European AI Act and in AI governance. In this paper, we highlight key challenges in testing for compliance with these requi…