Publications
Selected publications and links to full lists.
For complete publication lists, see:
A note for readers outside computer science: in CS, major conferences (e.g., FAccT, AIES, IJCAI, AAMAS, CHI) are archival, selective venues with full-paper peer review; they are weighted like, and often above, journal articles.
Selected Journal Articles
Meinel, P., Baum, K., Lauber-Rönsberg, A., Stenzel, L., & Langer, M. (2026). Human Oversight of AI Agents under the EU AI Act. Cambridge Forum on AI: Law and Governance. Accepted, to appear.
Schlicker, N., Baum, K., Uhde, A., Sterz, S., Hirsch, M.C., & Langer, M. (2025). How Do We Assess the Trustworthiness of AI? Introducing the Trustworthiness Assessment Model (TrAM). Computers in Human Behavior, 170. DOI
Langer, M., Baum, K., & Schlicker, N. (2024). Effective Human Oversight of AI-Based Systems: A Signal Detection Perspective. Minds and Machines, 35(1), 1–30. DOI
Biewer, S., Baum, K., Sterz, S., Hermanns, H., et al. (2024). Software Doping Analysis for Human Oversight. Formal Methods in System Design. DOI
Baum, K., & Sterz, S. (2022). Ethics for Nerds. The International Review of Information Ethics, 31(1). DOI
Baum, K., Mantel, S., Schmidt, E., & Speith, T. (2022). From Responsibility to Reason-Giving Explainable Artificial Intelligence. Philosophy & Technology, 35(1). DOI
Langer, M., Oster, D., Speith, T., Hermanns, H., Kästner, L., Schmidt, E., Sesing, A., & Baum, K. (2021). What Do We Want from Explainable Artificial Intelligence (XAI)? – A Stakeholder Perspective. Artificial Intelligence, 296. DOI
Selected Conference Papers
Ditz, J.C., Lazar, V., Lichtmeß, E., Plesch, C., Heck, M., Baum, K., & Langer, M. (2026). Secure Human Oversight of AI: Threat Modeling in a Socio-Technical Context. AIES 2026, Malmö. Best Poster Award. DOI
Baum, K., & Laux, J. (2026). Constitutive vs. Corrective: A Causal Taxonomy of Human Runtime Involvement in AI Systems. AISoLA 2026, Springer LNCS. DOI · arXiv
Jahn, F., Muskalla, Y., Dargasz, L., Schramowski, P., & Baum, K. (2026). Breaking Up with Normatively Monolithic Agency with GRACE: A Reason-Based Neuro-Symbolic Architecture for Safe and Ethical AI Alignment. IASEAI 2026, Paris. Proceedings
Baum, K., & Slavkovik, M. (2025). Aggregation Problems in Machine Ethics and AI Alignment. AIES 2025, Madrid. DOI
Steingrüber, A., & Baum, K. (2026). Justifications for Democratizing AI Alignment and Their Prospects. AISoLA 2025 Proceedings, Springer LNCS. DOI
Baum, K. (2026). Disentangling AI Alignment: A Structured Taxonomy Beyond Safety and Ethics. AISoLA 2024 Post-Proceedings, Springer LNCS. DOI
Sterz, S., Baum, K., Biewer, S., Hermanns, H., et al. (2024). On the Quest for Effectiveness in Human Oversight: Interdisciplinary Perspectives. FAccT 2024. DOI
Baum, K., Biewer, S., Hermanns, H., et al. (2025). Taming the AI Monster: Monitoring of Individual Fairness for Effective Human Oversight. SPIN 2024, Springer LNCS. DOI
Baum, K., Dargasz, L., Jahn, F., Gros, T.P., & Wolf, V. (2024). Acting for the Right Reasons: Creating Reason-Sensitive Artificial Moral Agents. FEAR Workshop @ iFM 2024. arXiv
Workshop Papers, Preprints, and Work Under Review
Baum, K., Binkytė, R., & Jahn, F. (2026). Norms at a Price: Why RL-Based Alignment Can Promise Conditional Compliance at Best. FAST Workshop @ NeurIPS 2026 (accepted full paper). arXiv
Baum, K., Kiener, M., Langer, M., & Laux, J. (2026). Anticipatory Human Oversight of Agentic AI: A Philosophical Account. Under review. Preprint
Gaube, S., Langer, M., Miller, T., Baum, K., et al. (2026). Keeping an Eye on AI: A Framework for Effective Human Oversight of AI Systems. Preprint
Baum, K., Schmidt, E., & Speith, T. (2026). The Reasons of AI Systems. Synthese, under revision.
Baum, K., Uth, R., Hermanns, H., et al. (2026). The Principal’s Principles: Actionable (Personalized) AI Alignment as Underexplored XAI Application Context. Contextualizing Explanations: Proceedings of the 3rd TRR 318 Conference. DOI
Book Chapters
Baum, K. (2026). Utilitarismus und das Problem kollektiven Handelns. In V. Andrić & B. Gesang (Eds.), Handbuch Utilitarismus (pp. 163–176). J.B. Metzler. DOI
Dissertation
Baum, K. (2024). Doing Wrong with Others – Multi-Agent Consequentialism as a Solution for the Collective Action Problem. TU Dortmund. (summa cum laude)