Michiel Bakker

Michiel Bakker

Assistant Professor, Massachusetts Institute of Technology

[last name]@mit.edu

Hi! I'm an Assistant Professor at MIT with appointments in the Institute for Data, Systems, and Society (IDSS), the business school (Sloan), the Laboratory for Information and Decision Systems (LIDS), and the Center for Constructive Communication (CCC) in the MIT Media Lab. My research focuses on large language models (LLMs), AI safety, AI governance, and the societal impacts of AI. Previously, I was a Research Scientist at Google DeepMind, where I worked on post-training and safety for the Gemini models.

Before that, I was a Computer Science PhD student at MIT, working with Alex "Sandy" Pentland at the MIT Media Lab. I also hold a bachelor's and master's degree in physics from TU Delft, where I worked on quantum computing at QuTech and IBM Quantum.

Lab

We work on AI alignment, AI governance and oversight, and AI for collective decision-making and epistemics. I work with students and postdocs across EECS, IDSS, and Sloan IT, and we all sit together in the MIT Schwarzman College of Computing. If you'd like to work with us, I'd encourage you to apply to those programs and reach out via [last name] [at] mit [dot] edu. Please put "[application]" in the subject line.

Postdocs
Joshua Yang
Luke Thorburn (incoming)
PhD Students
Elinor Poole-Dayan (co-advised with Mitchell Gordon and Jacob Andreas)
Haiwen Li
Prerna Ravi (co-advised with Hal Abelson)
Robin Na (co-advised with Abdullah Almaatouq)
Sulekha Kishore
Masters Students
Xiaoyang Cao

Our work is funded by the Cooperative AI Foundation, the Future of Life Foundation, the Foresight Institute, the Eric and Wendy Schmidt Fund for Strategic Innovation, and Galen Hines-Pierce.

Policy

I care a lot about making the transition to a post-AGI world go well, and I think policy work is a big part of that. I co-led the Nationaal AI Deltaplan, written at the request of the Dutch Ministry of Economic Affairs, and I co-wrote Europe 2031 (audio version), a scenario about what getting AI wrong would mean for Europe. It has been read by over a million people and was covered by the Economist, the Guardian, Bloomberg, and the New York Times, as well as many national media outlets across Europe.

Publications

Most recent publications on Google Scholar.
‡ indicates equal contribution.

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems
Xiaoyang Cao, Siddarth Srinivasan, Michiel A. Bakker
arXiv preprint. 2026.
A Roadmap to Impactful Pluralistic Alignment Research
Elinor Poole-Dayan, Jillian Fisher, Atoosa Kasirzadeh, Jacob Andreas, Mitchell Gordon, Michiel A. Bakker
arXiv preprint. 2026.
Position: Robust AI Personalization Will Require a Human Context Protocol
Anand V. Shah, Tobin South, Talfan Evans, Hannah Rose Kirk, Jiaxin Pei, Andrew Trask, E. Glen Weyl, Michiel A. Bakker
ICML'26: Forty-third International Conference on Machine Learning, Position Paper Track. 2026.
Emergent Misaligned Communication in Long-Horizon Multi-Agent LLM Commerce
Zeyuan Li, Lukas Petersson, Alessandro Acquisti, Michiel A. Bakker
arXiv preprint. 2026.
Belief Engine: Configurable and Inspectable Stance Dynamics in Multi-Agent LLM Deliberation
Joshua C. Yang, Maurice Flechtner, Damian Dailisan, Michiel A. Bakker
arXiv preprint. 2026.
AI and Collective Decisions: Strengthening Legitimacy and Losers' Consent
Suyash Fulay‡, Prerna Ravi‡, Emily Kubin, Shrestha Mohanty, Michiel A. Bakker, Deb Roy
arXiv preprint. 2026.
Multi-User Large Language Model Agents
Shu Yang, Shenzhe Zhu, Hao Zhu, José Ramón Enríquez, Di Wang, Alex Pentland, Michiel A. Bakker, Jiaxin Pei
arXiv preprint. 2026.
AI Assistance Reduces Persistence and Hurts Independent Performance
Grace Liu, Brian Christian, Tsvetomira Dumbalska, Michiel A. Bakker, Rachit Dubey
arXiv preprint. 2026.
AI Fact-Checking in the Wild: A Field Evaluation of LLM-Written Community Notes on X
Haiwen Li, Michiel A. Bakker
arXiv preprint. 2026.
Evaluating Human-AI Safety: A Framework for Measuring Harmful Capability Uplift
Michelle Vaccaro, Jaeyoon Song, Abdullah Almaatouq, Michiel A. Bakker
arXiv preprint. 2026.
Agora: Teaching the Skill of Consensus-Finding with AI Personas Grounded in Human Voice
Prerna Ravi, Om Gokhale, Suyash Fulay, Eugene Yi, Deb Roy, Michiel A. Bakker
arXiv preprint. 2026.
From Delegates to Trustees: How Optimizing for Long-Term Interests Shapes Bias and Alignment in LLMs
Suyash Fulay, Jocelyn Zhu, Michiel A. Bakker
EACL'26: Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics. 2026.
Benchmarking Overton Pluralism in LLMs
Elinor Poole-Dayan, Jiayi Wu, Taylor Sorensen, Jiaxin Pei, Michiel A. Bakker
International Conference on Learning Representations (ICLR). 2026.
RE-PO: Robust Enhanced Policy Optimization as a General Framework for LLM Alignment
Xiaoyang Cao, Zelai Xu, Mo Guang, Kaiwen Long, Michiel A. Bakker, Yu Wang, Chao Yu
International Conference on Learning Representations (ICLR). 2026.
AI and the Future of Digital Public Squares
Beth Goldberg, Diana Acosta-Navas, Michiel A. Bakker, Ian Beacock, Matt Botvinick, Prateek Buch, Renée DiResta, Nandika Donthi, Nathanael Fast, Ravi Iyer, Zaria Jalan, Andrew Konya, Grace Kwak Danciu, Hélène Landemore, Alice Marwick, Carl Miller, Aviv Ovadya, Emily Saltz, Lisa Schirch, Dalit Shalom, Divya Siddarth, Felix Sieker, Christopher Small, Jonathan Stray, Audrey Tang, Michael Henry Tessler, Amy Zhang
Collective Intelligence, 5(2). 2026.
Europe and the Geopolitics of AGI: The Need for a Preparedness Plan
Maximilian Negele, Daan Juijn, Afek Shamir, David Janků, Bengüsu Özcan, Lisa Soder, Lucia Velasco, Max Reddel, Michiel Bakker, Lorenzo Pacchiardi, Maksym Andriushchenko
RAND Corporation, RR-A4636-1. 2025.
The Impact of Advanced AI Systems on Democracy
Christopher Summerfield, Lisa P. Argyle, Michiel A. Bakker, Teddy Collins, Esin Durmus, Tyna Eloundou, Iason Gabriel, Deep Ganguli, Kobi Hackenburg, Gillian Hadfield, Luke Hewitt, Saffron Huang, Hélène Landemore, Nahema Marchal, Aviv Ovadya, Ariel Procaccia, Mathias Risse, Bruce Schneier, Elizabeth Seger, Divya Siddarth, Henrik Skaug Sætra, Michael Henry Tessler, Matthew Botvinick
Nature Human Behaviour, 9, 2420–2430. 2025.
Can AI Truly Represent Your Voice in Deliberations? A Comprehensive Study of Large-Scale Opinion Aggregation with LLMs
Shenzhe Zhu, Shu Yang, Michiel A. Bakker, Alex Pentland, Jiaxin Pei
arXiv preprint. 2025.
Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
Gheorghe Comanici, Eric Bieber, Mike Schaekermann, ..., Michiel A. Bakker, ... (3435 authors, ordered randomly)
arXiv preprint. 2025.
Scaling Human Judgment in Community Notes with LLMs
Haiwen Li, Soham De, Manon Revel, Andreas Haupt, Brad Miller, Keith Coleman, Jay Baxter, Martin Saveski, Michiel A. Bakker
Journal of Online Trust and Safety, 3(1). 2025.
Democratic AI is Possible. The Democracy Levels Framework Shows How It Might Work.
Aviv Ovadya, Kyle Redman, Luke Thorburn, Quan Ze Chen, Oliver Smith, Flynn Devine, Andrew Konya, Smitha Milli, Manon Revel, Kevin Feng, Amy X Zhang, Bilva Chandra, Michiel A. Bakker, Atoosa Kasirzadeh
Forty-second International Conference on Machine Learning (ICML). 2025.
Full-Stack Alignment: Co-Aligning AI and Institutions with Thick Models of Value
Joe Edelman, Tan Zhi-Xuan, Ryan Lowe, Oliver Klingefjord, Vincent Wang-Mascianica, Matija Franklin, Ryan Othniel Kearns, Ellie Hain, Atrisha Sarkar, Michiel A. Bakker, Fazl Barez, David Duvenaud, Jakob Foerster, Iason Gabriel, Joseph Gubbels, Bryce Goodman, Andreas Haupt, Jobst Heitzig, Julian Jara-Ettinger, Atoosa Kasirzadeh, James Ravi Kirkpatrick, Andrew Koh, W. Bradley Knox, Philipp Koralus, Joel Lehman, Sydney Levine, Samuele Marro, Manon Revel, Toby Shorin, Morgan Sutherland, Michael Henry Tessler, Ivan Vendrov, James Wilken-Smith
Preprint. 2025.
Value Profiles for Encoding Human Variation
Taylor Sorensen, Pushkar Mishra, Roma Patel, Michael Henry Tessler, Michiel Bakker, Georgina Evans, Iason Gabriel, Noah Goodman, Verena Rieser
EMNLP'25: Conference on Empirical Methods in Natural Language Processing. 2025.
Using Collective Dialogues and AI to Find Common Ground Between Israeli and Palestinian Peacebuilders
Andrew Konya, Luke Thorburn, Wasim Almasri, Oded Adomi Leshem, Ariel D. Procaccia, Lisa Schirch, Michiel A. Bakker
FAccT'25: Proceedings of the 2025 ACM Conference on Fairness, Accountability, and Transparency. 2025.
Tell Me Why: Incentivizing Explanations
Siddarth Srinivasan, Ezra Karger, Michiel Bakker, Yiling Chen
arXiv preprint. 2025.
Perceptual Interventions Ameliorate Statistical Discrimination in Learning Agents
Edgar A. Duéñez-Guzmán, Ramona Comanescu, Yiran Mao, Kevin R. McKee, Ben Coppin, Suzanne Sadedin, Silvia Chiappa, Alexander S. Vezhnevets, Michiel A. Bakker, Yoram Bachrach, William Isaac, Karl Tuyls, Joel Z. Leibo
Proceedings of the National Academy of Sciences (PNAS), 122(25), e2319933121. 2025.
Can AI Mediation Improve Democratic Deliberation?
Michael Henry Tessler, Georgina Evans, Michiel A. Bakker, Iason Gabriel, Sophie Bridgers, Rishub Jain, Raphael Koster, Verena Rieser, Anca Dragan, Matthew Botvinick, Christopher Summerfield
Artificial Intelligence and Democratic Freedoms, Knight First Amendment Institute. 2025.
Supernotes: Driving Consensus in Crowd-Sourced Fact-Checking
Soham De, Michiel A. Bakker, Jay Baxter, Martin Saveski
WWW'25: Proceedings of the ACM Web Conference 2025, 3751–3761. 2025.
AI can help humans find common ground in democratic deliberation
Michael Henry Tessler‡, Michiel A. Bakker‡, Daniel Jarrett, Hannah Sheahan, Martin J. Chadwick, Raphael Koster, Georgina Evans, Lucy Campbell-Gillingham, Tantum Collins, David C. Parkes, Matthew Botvinick, Christopher Summerfield
Science. 2024.
How large language models can reshape collective intelligence
Jason W. Burton, Ezequiel Lopez-Lopez, Shahar Hechtlinger, Zoe Rahwan, Samuel Aeschbach, Michiel A. Bakker, Joshua A. Becker, Aleks Berditchevskaia, Julian Berger, Levin Brinkmann, Lucie Flek, Stefan M. Herzog, Saffron Huang, Sayash Kapoor, Arvind Narayanan, Anne-Marie Nussberger, Taha Yasseri, Pietro Nickl, Abdullah Almaatouq, Ulrike Hahn, Ralf H. J. M. Kurvers, Susan Leavy, Iyad Rahwan, Divya Siddarth, Alice Siu, Anita W. Woolley, Dirk U. Wulff, Ralph Hertwig
Nature Human Behaviour. 2024.
Language agents as digital representatives in collective decision-making
Daniel Jarrett, Miruna Pislar, Michiel A. Bakker, Michael Henry Tessler, Raphael Koster, Jan Balaguer, Romuald Elie, Christopher Summerfield, Andrea Tacchetti
NeurIPS'23 Workshop on Foundation Models for Decision Making. 2023.
Scaffolding cooperation in human groups with deep reinforcement learning
Kevin R. McKee, Andrea Tacchetti, Michiel A. Bakker, Jan Balaguer, Lucy Campbell-Gillingham, Richard Everett, Matthew M. Botvinick
Nature Human Behaviour. 2023.
Fine-tuning language models to find agreement among humans with diverse preferences
Michiel A. Bakker‡, Martin J. Chadwick‡, Hannah R. Sheahan‡, Michael Henry Tessler, Lucy Campbell-Gillingham, Jan Balaguer, Nat McAleese, Amelia Glaese, John Aslanides, Matthew M. Botvinick, Christopher Summerfield
NeurIPS'22: Advances in Neural Information Processing Systems. 2022.
Quantifying the importance and location of SARS-CoV-2 transmission events in large metropolitan areas
Alberto Aleta, David Martín-Corral, Michiel A. Bakker, Ana Pastore y Piontti, Marco Ajelli, Maria Litvinova, Matteo Chinazzi, Natalie E. Dean, M. Elizabeth Halloran, Ira M. Longini Jr, Alex Pentland, Alessandro Vespignani, Yamir Moreno, Esteban Moro
Proceedings of the National Academy of Sciences (PNAS). 2022.
Modelling Cooperation in Network Games with Spatio-Temporal Complexity
Michiel A. Bakker‡, Richard Everett‡, Laura Weidinger, Iason Gabriel, William S. Isaac, Joel Z. Leibo, Edward Hughes
AAMAS'21: Conference on Autonomous Agents and Multiagent Systems. 2021.
Beyond Reasonable Doubt: Improving Fairness in Budget-Constrained Decision Making using Confidence Thresholds
Michiel A. Bakker, Duy Patrick Tu, Krishna P. Gummadi, Alex Pentland, Kush R. Varshney, Adrian Weller
AIES'21: Fourth AAAI/ACM Conference on AI, Ethics, and Society. 2021.
Algorithmic Targeting of Social Policies: Fairness, Accuracy, and Distributed Governance
Alejandro Noriega-Campero, Bernardo Garcia-Bulle, Luis Fernando Cantu, Michiel A. Bakker, Luis Tejerina, Alex Pentland
FAccT‡'20: ACM Conference on Fairness, Accountability, and Transparency. 2020.
Assessing Disease Exposure Risk with Location Data: A Proposal for Cryptographic Preservation of Privacy
Alex Berke, Michiel A. Bakker, Praneeth Vepakomma, Kent Larson, Alex Pentland
arXiv preprint. 2020.
VizNet: Towards A Large-Scale Visualization Learning and Benchmarking Repository
Kevin Z. Hu, Neil Gaikwad, Madelon Hulsebos, Michiel A. Bakker, Emanuel Zgraggen, César A Hidalgo, Tim Kraska, Guoliang Li, Arvind Satyanarayan, Cagatay Demiralp
CHI'19: Conference on Human Factors in Computing Systems. 2019.
Sherlock: A Deep Learning Approach to Semantic Data Type Detection
Madelon Hulsebos‡, Kevin Z. Hu‡, Michiel A. Bakker, Emanuel Zgraggen, Arvind Satyanarayan, Tim Kraska, Çagatay Demiralp, César A. Hidalgo
KDD'19: Conference on Knowledge Discovery and Data Mining. 2019.
VizML: A Machine Learning Approach to Visualization Recommendation
Kevin Z. Hu, Michiel A. Bakker, Stephen Li, Tim Kraska, César A. Hidalgo
CHI'19: Conference on Human Factors in Computing Systems. 2019.
Atomic-scale imaging of a 27-nuclear-spin cluster using a quantum sensor
Mohamed H. Abobeih, Joe Randall, Conor E. Bradley, Hans P. Bartling, Michiel A. Bakker, Maarten J. Degen, Matthew Markham, Daniel J. Twitchen, Tim H. Taminiau
Nature. 2019.
A Ten-Qubit Solid-State Spin Register with Quantum Memory up to One Minute
Conor E. Bradley, Joe Randall, Mohamed H. Abobeih, Remon C. Berrevoets, Maarten J. Degen, Michiel A. Bakker, Matthew Markham, Daniel J. Twitchen, Tim H. Taminiau
Physical Review X. 2019.
Measuring fine-grained multidimensional integration using mobile phone metadata: the case of Syrian refugees in Turkey
Michiel A. Bakker, Daoud A. Piracha, Patricia J. Lu, Keis Bejgo, Mohsen Bahrami, Yan Leng, Jose Balsa-Barreiro, Julie Ricard, Alfredo J. Morales, Vivek K. Singh, Burcin Bozkaya, Selim Balcisoy, Alex Pentland
Guide to Mobile Data Analytics in Refugee Scenarios, Springer. 2019.
DADI: Dynamic Discovery of Fair Information with Adversarial Reinforcement Learning
Michiel A. Bakker, Duy Patrick Tu, Humberto Riverón Valdés, Krishna P. Gummadi, Kush R. Varshney, Adrian Weller, Alex Pentland
NeurIPS Workshop on Human-Centric Machine Learning. 2019.
Active Fairness in Algorithmic Decision Making
Alejandro Noriega-Campero‡, Michiel A. Bakker‡, Bernardo Garcia-Bulle, Alex Pentland
AIES'19: Second AAAI/ACM Conference on AI, Ethics, and Society. 2019.
On Fairness in Budget-Constrained Decision Making
Michiel A. Bakker, Alejandro Noriega-Campero, Duy Patrick Tu, Prasanna Sattigeri, Kush R. Varshney, Alex Pentland
KDD Workshop on Explainable AI. 2019.
One-second coherence for a single electron spin coupled to a multi-qubit nuclear-spin environment
Mohamed H. Abobeih, Julia Cramer, Michiel A. Bakker, Norbert Kalb, Matthew Markham, Daniel J. Twitchen, Tim H. Taminiau
Nature Communications. 2018.
Validity of the single-particle description and charge noise resilience for multielectron quantum dots
Michiel A. Bakker‡, Sebastian Mehl‡, Tuukka Hiltunen, Ari Harju, David P. DiVincenzo
Physical Review B. 2015.
The Tipsy Single Soft Photon Detector and the Trixy Ultrafast Tracking Detector
Harry van der Graaf, Michiel A. Bakker, Hong W. Chan, Edoardo Charbon, Fabio Santagata, Pasqualina M. Sarro, Dennis R. Schaart
Journal of Instrumentation. 2013.

Experience

2024 - present
Assistant Professor · MIT
Sloan School of Management
Institute for Data, Systems, and Society (IDSS)
Laboratory for Information and Decision Systems (LIDS)
2021 - 2026
Senior Research Scientist · Google DeepMind
Post-training and safety for the Gemini models
2017 - 2020
Ph.D. Student · MIT
Computer Science
2019
Research Intern · Google DeepMind
Ethics Research Team, Multi-Agent
2015
Research Intern · IBM Research
Quantum Computing
2015 - 2016
Co-Founder and Managing Director UK · Bloomon
E-commerce flower startup
2014 - 2015
Master Thesis · QuTech, TU Delft
Quantum Computing in Diamond
2014
Research Intern · RWTH Aachen
Quantum Computing in Singlet-Triplet Qubits
2013 - 2014
Co-Founder and Country Manager · Lamudi Myanmar
Rocket Internet, Online real estate platform
2012 - 2015
M.Sc. Student · TU Delft
Physics, Cum Laude, Top 5% GPA
Took a one-year entrepreneurial break in Myanmar.
2012
Bachelor Thesis · CERN and Nikhef
Electron Emission Membranes
2008 - 2012
B.Sc. Student · TU Delft
Physics

Website Design

Based on the homepage of my collaborator (and friend!) Martin Saveski and my friend Jacques Carolan.