GH
Gillian K. Hadfield
cs.AIcs.CYcs.MAcs.CLecon.GNq-fin.ECArtificial Intelligencecs.LGPoliticsadaptability
On Valency
published · living versionsW_pnd25zpr·v1 · currentpublished
NormGym: Evaluating Normative Competence through Social Interaction
with Binze Li, Zihuan Zhang, Seokhyun Baek, Tianmin Shu
1 version
Preprints & journals
31 papers in the corpus · 2009–2026Comprehension Audits to Mitigate Risks from Automated AI Research2610.10064v1 · Ronald J. Bodkin, Bahrad A. Sokhansanj, Gillian K. Hadfield2026 · 0 citationsarXiv
Legal infrastructure for transformative AI governance.42475560 · Hadfield, Gillian K2026 · 0 citationsProceedings of the National Academy of Sciences of the United States of America. 2026;123(30):e2509742123
Talk, Judge, Cooperate: Gossip-Driven Indirect Reciprocity in Self-Interested LLM Agents2602.07777v2 · Shuhui Zhu, Yue Lin, Shriya Kaistha et al.2026 · 0 citationsarXiv
Legal Alignment for Safe and Ethical AI2601.04175v2 · Noam Kolt, Nicholas Caputo, Jack Boeglin et al.2026 · 4 citationsarXiv
Metanorms generate stable yet adaptable normative social order in a politically decentralized society.41537884 · Mathew, Sarah, Hadfield, Gillian K, Mwangi, Danson et al.2026 · 2 citationsPhilosophical transactions of the Royal Society of London. Series B, Biological sciences. 2025;380(1940)
The impact of advanced AI systems on democracy.41034566 · Summerfield, Christopher, Argyle, Lisa P, Bakker, Michiel et al.2025 · 16 citationsNature human behaviour. 2025;9(12):2420-2430
Talk Isn't Always Cheap: Understanding Failure Modes in Multi-Agent Debate2509.05396v2 · Andrea Wynn, Harsh Satija, Gillian Hadfield2025 · 1 citationarXiv
Societal Alignment Frameworks Can Improve LLM Alignment2503.00069v2 · Karolina Sta'nczak, Nicholas Meade, Mehar Bhatia et al.2025 · 0 citationsarXiv
Multi-Agent Risks from Advanced AI2502.14143v1 · Lewis Hammond, Alan Chan, Jesse Clifton et al.2025 · 12 citationsarXiv
Infrastructure for AI Agents2501.10114v3 · Alan Chan, Kevin Wei, Sihao Huang et al.2025 · 4 citationsarXiv
AI Model Registries: A Foundational Tool for AI Governance2410.09645v1 · Elliot McKernon, Gwyn Glasser, Deric Cheng et al.2024 · 5 citationsarXiv
How will advanced AI systems impact democracy?2409.06729v1 · Christopher Summerfield, Lisa Argyle, Michiel Bakker et al.2024 · 5 citationsarXiv
Normative Modules: A Generative Agent Architecture for Learning Norms that Supports Multi-Agent Cooperation2405.19328v1 · Atrisha Sarkar, Andrei Ioan Muresanu, Carter Blair et al.2024 · 0 citationsarXiv
Managing extreme AI risks amid rapid progress.38768279 · Bengio, Yoshua, Hinton, Geoffrey, Yao, Andrew et al.2024 · 347 citationsScience (New York, N.Y.). 2024;384(6698):842-845
Regulating advanced artificial agents.38574134 · Cohen, Michael K, Kolt, Noam, Bengio, Yoshua et al.2024 · 45 citationsScience (New York, N.Y.). 2024;384(6691):36-38
Responsible Reporting for Frontier AI Development2404.02675v1 · Noam Kolt, Markus Anderljung, Joslyn Barnhart et al.2024 · 6 citationsarXiv
Rational Silence and False Polarization: How Viewpoint Organizations and Recommender Systems Distort the Expression of Public Opinion2403.06264v2 · Atrisha Sarkar, Gillian K. Hadfield2024 · 1 citationarXiv
Computing Power and the Governance of Artificial Intelligence2402.08797v1 · Girish Sastry, Lennart Heim, Haydn Belfield et al.2024 · 26 citationsarXiv
International Institutions for Advanced AI2307.04699v2 · Lewis Ho, Joslyn Barnhart, Robert Trager et al.2023 · 21 citationsarXiv
Frontier AI Regulation: Managing Emerging Risks to Public Safety2307.03718v4 · Markus Anderljung, Joslyn Barnhart, Anton Korinek et al.2023 · 77 citationsarXiv
Judging facts, judging norms: Training machine learning models to judge humans requires a modified approach to labeling data.37163590 · Balagopalan, Aparna, Madras, David, Yang, David H et al.2023 · 14 citationsScience advances. 2023;9(19):eabq0701
Regulatory Markets: The Future of AI Governance2304.04914v5 · Gillian K. Hadfield, Jack Clark2023 · 23 citationsJurimetrics: The Journal of Law, Science and Technology, Volume 65 pp. 195-240 (2026)
Gathering Strength, Gathering Storms: The One Hundred Year Study on Artificial Intelligence (AI100) 2021 Study Panel Report2210.15767v1 · Michael L. Littman, Ifeoma Ajunwa, Guy Berger et al.2022 · 142 citationsarXiv
Cooperative AI: machines must learn to find common ground.33947992 · Dafoe, Allan, Bachrach, Yoram, Hadfield, Gillian et al.2021 · 232 citationsNature. 2021;593(7857):33-36
Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims2004.07213v2 · Miles Brundage, Shahar Avin, Jasmine Wang et al.2020 · 305 citationsarXiv
Silly rules improve the capacity of agents to learn stable enforcement and compliance behaviors2001.09318v1 · Raphael Koster, Dylan Hadfield-Menell, Gillian K. Hadfield et al.2020 · 9 citationsarXiv
Regulatory Markets for AI Safety2001.00078v2 · Jack Clark, Gillian K. Hadfield2019 · 33 citationsarXiv
The Role of Cooperation in Responsible AI Development1907.04534v1 · Amanda Askell, Miles Brundage, Gillian Hadfield2019 · 48 citationsarXiv
Legible Normativity for AI Alignment: The Value of Silly Rules1811.01267v1 · Dylan Hadfield-Menell, McKane Andrus, Gillian K. Hadfield2018 · 2 citationsarXiv
Incomplete Contracting and AI Alignment1804.04268v1 · Dylan Hadfield-Menell, Gillian Hadfield2018 · 83 citationsarXiv
Toward a 21st-century health care system: recommendations for health care reform.19258550 · Arrow, Kenneth, Auerbach, Alan, Bertko, John et al.2009 · 80 citationsAnnals of internal medicine. 2009;150(7):493-5
Career total: 145 works. 31 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.