Kevin Baum
Deputy Head of NMM
Research Group Leader
Senior Scientist/PostDoc
DFKI – Neuro-Mechanistic Modeling
RAIME – Responsible AI and Machine Ethics
CERTAIN
Saarland Informatics Campus
Campus D3.2 (DFKI)
66123 Saarbrücken
Germany
About Me
I’m a philosopher (Dr. phil.) and computer scientist (M.Sc.) working on AI alignment and human-centered control. I lead the research group Responsible AI and Machine Ethics (RAIME) at DFKI and serve as Deputy Head of the Neuro-Mechanistic Modeling department. I’m also a Saarland University Associate Fellow with PhD supervision rights in Computer Science, a Research Associate at the Oxford Internet Institute, University of Oxford, and a Senior Researcher at the Institute for Ethics in Technology at Hamburg University of Technology. I serve on the executive board of CERTAIN, the Center for European Research in Trusted AI. I co-initiated the award-winning lecture series Ethics for Nerds at Saarland University and co-founded Algoright e.V.
Research
My research asks three questions:
- What norms should AI agents answer to, and who gets to decide? How can the relevant normative expectations be gathered in practice and represented technically?
- How can we build agents that follow these norms whether or not they expect to be watched, in a way that stays contestable and can be improved over time?
- How do humans keep effective oversight and control, so that AI is safe and moral responsibility and human autonomy are preserved?
At RAIME we approach these questions with both philosophical and technical methods. This includes reason-based neuro-symbolic architectures for agents that follow norms (GRACE), work on the limits of RL-based alignment, and interdisciplinary research on what makes human oversight effective, including under the EU AI Act. I have pursued these questions in several interdisciplinary projects, including Explainable Intelligent Systems (EIS), project E7 of the Transregional Collaborative Research Centre 248 “Foundations of Perspicuous Software Systems” (CPEC), and MAC-MERLin.
Interests
- AI Alignment
- Human Oversight
- AI Control
- Machine Ethics
- Normative Reasoning
- AI Governance
Publications (37)
2026
AI CHAOS! 2nd Workshop on the Challenges for Human Oversight of AI Systems
2026 — CHI EA ‘26: Proceedings of the Extended Abstracts of the 2026 CHI Conference on Human Factors in Computing Systems. International Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA-26), April 13-17, Barcelona, Spain
Utilitarismus und das Problem kollektiven Handelns
2026 — Handbuch Utilitarismus
What are AI systems? Rethinking the core definition in the EU AI Act
2026 — Computer Law & Security Review
2025
A Roadmap for Responsible Robotics: Promoting Human Agency and Collaborative Efforts
2025 — IEEE Robotics & Automation Magazine
Aggregation Problems in Machine Ethics and AI Alignment
2025 — Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society. AAAI/ACM Conference on Artificial Intelligence, Ethics, and Society (AIES-2025)
Disentangling AI Alignment: A Structured Taxonomy Beyond Safety and Ethics
2025 — AISoLA 2024. International Conference on Bridging the Gap between AI and Reality (AiSoLA-2024)
How do we assess the trustworthiness of AI? Introducing the trustworthiness assessment model (TrAM)
2025 — Computers in Human Behavior
Justifications for Democratizing AI Alignment and Their Prospects
2025 — AISoLA 2025. International Conference on Bridging the Gap between AI and Reality (AiSoLA-2025)
Let’s Talk AI with philosophy and computer science expert Kevin Baum
2025 — Let’s Talk AI: Interdisciplinarity Is a Must
On the Complexities of Testing for Compliance with Human Oversight Requirements in AI Regulation
2025 — International Conference on Bridging the Gap between AI and Reality. International Conference on Bridging the Gap between AI and Reality (AiSoLA-2025)
Responsible and Trusted AI: An Interdisciplinary Perspective (2025)
2025 — International Conference on Bridging the Gap between AI and Reality. International Conference on Bridging the Gap between AI and Reality (AiSoLA-2025)
2024
Responsible and Trusted AI: An Interdisciplinary Perspective
2024 — Bridging the Gap Between AI and Reality - Second International Conference, Proceedings. International Conference on Bridging the Gap between AI and Reality (AiSoLA-2024), October 30 - November 3, Crete, Greece
Transparent Transparency Developing a Scheme for Understanding Transparency Requirements
2024 — Bridging the Gap Between AI and Reality - Second International Conference, Proceedings. International Conference on Bridging the Gap between AI and Reality (AiSoLA-2024), October 30 - November 3, Crete, Greece
2024 — Minds and Machines - Journal for Artificial Intelligence, Philosophy and Cognitive Science
Taming the AI Monster: Monitoring of Individual Fairness for Effective Human Oversight
2024 — Model Checking Software - 30th International Symposium - Proceedings. International Symposium on Model Checking Software (SPIN-2024), April 8-9, Luxembourg City, Luxembourg
Acting for the Right Reasons: Creating Reason-Sensitive Artificial Moral Agents
2024 — ArXiv e-prints (arxiv)
Software doping analysis for human oversight
2024 — Formal Methods in System Design
On the Quest for Effectiveness in Human Oversight: Interdisciplinary Perspectives
2024 — Proceedings of the 2024 ACM Conference on Fairness, Accountability, and Transparency. ACM Conference on Fairness, Accountability, and Transparency (ACM FAccT-2024), June 3-6, Rio de Janeiro, Brazil
2023
From Fear to Action: AI Governance and Opportunities for All
2023 — Frontiers in Computer Science
Normative Perspectives on and Societal Implications of AI Systems
2023 — AISoLA 2023. International Conference on Bridging the Gap between AI and Reality (AiSoLA-2023), Kreta
XAI Requirements in Smart Production Processes: A Case Study
2023 — Explainable Artificial Intelligence, First World Conference, Proceedings, Part I. xAI: World Conference on Explainable Artificial Intelligence (xAI-2023), July 26-28, Lissabon, Portugal
2022
2022 — The International Review of Information Ethics (IRIE)
From Responsibility to Reason-Giving Explainable Artificial Intelligence
2022 — Philosophy & Technology
2021
2021 — International Journal of Selection and Assessment
Towards Perspicuity Requirements
2021 — 2021 IEEE 29th International Requirements Engineering Conference Workshops (REW). IEEE International Requirements Engineering Conference (RE-2021)
2021 — Computers in Human Behavior
2020
2020 — Folge um Folge. Multiple Perspektiven auf die Fernsehserie
Algorithmen und die Grenzen von Fairness
2020 — Kevin Baum; Tina Feldkamp; Sophie Elisabeth Henning; Nikolai Käfer; Andreas Suchanek; Wolfgang Gründinger; Sarah J. Becker; André T. Nemat; Marcel Rebbert; Robert Ranisch; Lisa Schöttl; Manuel Kilian; Pauline Kuss; Philipp Hommelsheim; Simon Dümpelmann;: Unternehmensverantwortung im digitalen Wandel: Ein Debattenbeitrag zu Corporate Digital Responsibility
2019
Explainability as a Non-Functional Requirement
2019 — 2019 IEEE 27th International Requirements Engineering Conference (RE). IEEE International Requirements Engineering Conference (RE-2019)
2019 — 18. GI-Fachtagung Informatik und Schule. Informatik für alle. GI-Fachtagung Informatik und Schule (INFOS-2019), September 16-18, Dortmund, Germany
2018
Algorithmen bei der Personalauswahl – eine kritische und hoffnungsvolle Betrachtung
2018 — Wirtschaftspsychologie aktuell
2018 — Dr. Markus Langer; Kevin Baum; Prof. Dr. Cornelius J. König;: Mensch und Gesellschaft im digitalen Wandel
From Machine Ethics to Machine Explainability and Back
2018 — International Symposium on Artificial Intelligence and Mathematics (ISAIM). International Symposium on Artificial Intelligence and Mathematics, ISAIM 2018
2017
Two Challenges for CI Trustworthiness and How to Address Them
2017 — Proceedings of the 1st Workshop on Explainable Computational Intelligence (XCI 2017). Explainable Computational Intelligence Workshop (XCI-2017), located at INLG 2017, September 4, Santiago de Compostela, Spain
2016
2016 — WSCG 2016. Short Papers Proceedings - 24th International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision. International Conference on Computer Graphics, Visualization and Computer Vision (WSCG-2016), May 30 - June 3, Plzen, Czech Republic
What the hack is wrong with software doping?
2016 — International Symposium on Leveraging Applications of Formal Methods. International Symposium On Leveraging Applications of Formal Methods, Verification and Validation (ISoLA-2016)