Dr. Kevin Baum

I’m Kevin Baum — ethicist (Dr. phil.) and computer scientist (M.Sc.) working at the intersection of philosophy, AI, and policy.

Current positions:

Independent Research Group Leader, Responsible AI and Machine Ethics (RAIME) at the German Research Center for Artificial Intelligence (DFKI)
Saarland University Associate Fellow, Saarland Informatics Campus (with PhD supervision rights in Computer Science)
Senior Researcher (from April 2026), Institute for Ethics in Technology, Hamburg University of Technology

I also serve on the executive board of the Center for European Research in Trusted AI (CERTAIN) and am a member of the International Association for Safe and Ethical AI (IASEAI), founded by Stuart Russell.

What I work on:

My research bridges normative theory and technical practice. I focus on making AI systems that are not just capable, but trustworthy, fair, and aligned with human values — and on understanding what those terms should actually mean.

Core themes include:

Effective human oversight of AI systems (not just humans “in the loop,” but humans genuinely in control, meant to be an additional layer of safety)
Machine ethics and building AI agents that are sensitive to normative reasons
Algorithmic fairness and the operationalization of “Trustworthy AI”
Explainability as a bridge between technical systems and human understanding

I approach these questions with tools from philosophy (metaethics, practical reasoning, collective action theory) and computer science (reinforcement learning, mechanistic interpretability, formal methods).

→ More about my research

Beyond the lab:

I co-founded Algoright e.V., a think tank for responsible digitalization, and have advised policy makers and public administration on AI ethics and governance issues. In 2024, I was part of the German delegation to the UK-German Science, Innovation and Technology Dialogue.

Our course Ethics for Nerds won the “Hochschulperle des Jahres” (2019) from the German Stifterverband.

→ Teaching & Engagement

Get in touch:

For my full academic CV, see here. For speaking inquiries, consulting, or collaboration: academia@kevinbaum.de

selected publications

IEEE R&A

A Roadmap for Responsible Robotics: Promoting Human Agency and Collaborative Efforts

Dejanira Araiza-Illan, Kevin Baum, Helen Beebee, and 28 more authors

IEEE Robotics & Automation Magazine, 2025

Bib

@article{11236462,
  author = {Araiza-Illan, Dejanira and Baum, Kevin and Beebee, Helen and Chatila, Raja and Moth-Lund Christensen, Sarah and Coghlan, Simon and Collins, Emily and Conroy, S. Kate and Cunha, Alcino and Dobrosovestnova, Anna and Duijf, Hein and Evers, Vanessa and Fisher, Michael and Hochgeschwender, Nico and Kökciyan, Nadin and Lemaignan, Séverin and Rodriguez-Lera, Francisco and Ljungblad, Sara and Magnusson, Martin and Mansouri, Masoumeh and Milford, Michael and Moon, AJung and Powers, Thomas M. and Salvini, Pericle and Scantamburlo, Teresa and Schuster, Nick and Slavkovik, Marija and Topcu, Ufuk and Vanegas, Daniel and Wasowski, Andrzej and Yang, Yi},
  journal = {IEEE Robotics \& Automation Magazine},
  title = {{A Roadmap for Responsible Robotics: Promoting Human Agency and Collaborative Efforts}},
  year = {2025},
  pages = {2--14},
  doi = {10.1109/MRA.2025.3620148},
}

CHB

How Do We Assess the Trustworthiness of AI? Introducing the Trustworthiness Assessment Model (TrAM)

Nadine Schlicker, Kevin Baum, Alarith Uhde, and 3 more authors

Computers in Human Behavior, 2025

Bib

@article{schlickertrust2025,
  title = {{How Do We Assess the Trustworthiness of AI? Introducing the Trustworthiness Assessment Model (TrAM)}},
  author = {Schlicker, Nadine and Baum, Kevin and Uhde, Alarith and Sterz, Sarah and Hirsch, Martin C and Langer, Markus},
  journal = {Computers in Human Behavior},
  volume = {170},
  pages = {108671},
  year = {2025},
  publisher = {Elsevier},
  doi = {10.1016/j.chb.2025.108671},
}

M&M

Effective Human Oversight of AI-Based Systems: A Signal Detection Perspective on the Detection of Inaccurate and Unfair Outputs

Markus Langer, Kevin Baum, and Nadine Schlicker

Minds and Machines, 2024

Bib

@article{Langer2024-LANEHO-2,
  author = {Langer, Markus and Baum, Kevin and Schlicker, Nadine},
  doi = {10.1007/s11023-024-09701-0},
  journal = {Minds and Machines},
  number = {1},
  pages = {1--30},
  title = {{Effective Human Oversight of AI-Based Systems: A Signal Detection Perspective on the Detection of Inaccurate and Unfair Outputs}},
  volume = {35},
  year = {2024},
}

FMSD

Software Doping Analysis for Human Oversight

Sebastian Biewer, Kevin Baum, Sarah Sterz, and 5 more authors

Formal Methods in System Design, 2024

Bib

@article{biewer2023software,
  title = {{Software Doping Analysis for Human Oversight}},
  author = {Biewer, Sebastian and Baum, Kevin and Sterz, Sarah and Hermanns, Holger and Hetmank, Sven and Langer, Markus and Lauber-Rönsberg, Anne and Lehr, Franz},
  year = {2024},
  journal = {Formal Methods in System Design},
  doi = {10.1007/s10703-024-00445-2},
  url = {https://arxiv.org/abs/2308.06186},
}

P&T

From Responsibility to Reason-Giving Explainable Artificial Intelligence

Kevin Baum, Susanne Mantel, Eva Schmidt, and 1 more author

Philosophy & Technology, 2022

Bib

@article{baum2022responsibility,
  title = {{From Responsibility to Reason-Giving Explainable Artificial Intelligence}},
  author = {Baum, Kevin and Mantel, Susanne and Schmidt, Eva and Speith, Timo},
  journal = {Philosophy \& Technology},
  volume = {35},
  number = {1},
  year = {2022},
  doi = {10.1007/s13347-022-00510-w},
  publisher = {Springer International Publishing},
}

What Do We Want from Explainable Artificial Intelligence (XAI)? – A Stakeholder Perspective on XAI and a Conceptual Model Guiding Interdisciplinary XAI Research

Markus Langer, Daniel Oster, Timo Speith, and 5 more authors

Artificial Intelligence, 2021

Bib

@article{langer2021we,
  title = {{What Do We Want from Explainable Artificial Intelligence (XAI)? -- A Stakeholder Perspective on XAI and a Conceptual Model Guiding Interdisciplinary XAI Research}},
  author = {Langer, Markus and Oster, Daniel and Speith, Timo and Hermanns, Holger and Kästner, Lena and Schmidt, Eva and Sesing, Andreas and Baum, Kevin},
  journal = {Artificial Intelligence},
  volume = {296},
  year = {2021},
  doi = {10.1016/j.artint.2021.103473},
  publisher = {Elsevier},
}

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, and 2 more authors

In , 2026

Accepted for the proceedings of the 2nd Conference of the International Association for Safe and Ethical Artificial Intelligence (IASEAI 2026), Paris, France, Feb 24–26, 2026

Bib

@inproceedings{jahn2025breaking,
  author = {Jahn, Felix and Muskalla, Yannic and Dargasz, Lisa and Schramowski, Patrick and Baum, Kevin},
  title = {{Breaking Up with Normatively Monolithic Agency with GRACE: A Reason-Based Neuro-Symbolic Architecture for Safe and Ethical AI Alignment}},
  year = {2026},
  note = {Accepted for the proceedings of the 2nd Conference of the International Association for Safe and Ethical Artificial Intelligence (IASEAI 2026), Paris, France, Feb 24--26, 2026},
  doi = {10.48550/arXiv.2601.10520},
}

AIES

Aggregation Problems in Machine Ethics and AI Alignment

Kevin Baum, and Marija Slavkovik

In Proceedings of the 8th AAAI/ACM Conference on AI, Ethics, and Society (AIES 2025), Madrid, Spain, Oct 20–22, 2025, 2025

Bib

@inproceedings{BaumSlavkovik2025,
  author = {Baum, Kevin and Slavkovik, Marija},
  title = {{Aggregation Problems in Machine Ethics and AI Alignment}},
  booktitle = {Proceedings of the 8th AAAI/ACM Conference on AI, Ethics, and Society (AIES 2025), Madrid, Spain, Oct 20--22, 2025},
  year = {2025},
  address = {Madrid, Spain},
  publisher = {ACM},
  doi = {10.1609/aies.v8i1.36554},
}

FAccT

On the Quest for Effectiveness in Human Oversight: Interdisciplinary Perspectives

Sarah Sterz, Kevin Baum, Sebastian Biewer, and 4 more authors

In , Jun 2024

Proceedings of the 2024 ACM Conference on Fairness, Accountability, and Transparency (FAccT 2024)

Bib

@inproceedings{sterz2024,
  author = {Sterz, Sarah and Baum, Kevin and Biewer, Sebastian and Hermanns, Holger and Lauber-Rönsberg, Anne and Meinel, Philip and Langer, Markus},
  title = {{On the Quest for Effectiveness in Human Oversight: Interdisciplinary Perspectives}},
  month = jun,
  year = {2024},
  note = {Proceedings of the 2024 ACM Conference on Fairness, Accountability, and Transparency (FAccT 2024)},
  doi = {10.1145/3630106.3659051},
}