Published/Accepted Articles: (Google scholar)

Philosophy, Ethics, Safety of AI and Science

(24) We Need to Understand the Effect of Narratives about Generative AI (with Fabrizio Gilardi, Anita Gohdes, et al.) [paper]  
Nature Human Behavior; 2024

(23) Two Types of AI Existential Risks: Decisive and Accumulative  
Philosophical Studies; Accepted

(22) Foundational Challenges in Assuring Alignment and Safety of Large Language Models (with Usman Anwar et al.) [paper]
Transactions in Machine Learning Research; 2024

(21) Epistemic Injustice in Generative AI (with Jackie Kay and Shakir Mohammed) [paper]
AAAI/ACM Proceedings of AI, Ethics, Society (AIES); 2024

(20) CIVICS: Buiding a Dataset for Examining Culturally-Informed Values in Large Language Models (with Giada Pistilli et al.) [paper]
AAAI/ACM Proceedings of AI, Ethics, Society (AIES); 2024

(19) Beyond Model Interpretability: Socio-structural Explanations in Machine Learning (with Andrew Smart) [paper]
AI & Society; 2024

(18) Explanation Hacking: The Perils of Algorithmic Recourse (with Emily Sullivan)  
Book Chapter in “Philosophy of Science for Machine Learning: Core Issues and New Perspectives“, Springer, Forthcoming

(17) Intelligent Capacities in Artificial Systems (with Victoria McGeer) 
Book Chapter in “Artificial Dispositions: Metaphysical and Ethical Issues”; Bloomsburg Publishing, 2023

(16) User Tampering in Reinforcement Learning Recommender Systems (with Charles Evans) [draft, proceedings]
AAAI/ACM Proceedings of AI, Ethics, Society (AIES); 2023

(15)  Typology of Risks of Generative Text-to-Image Models (with Charlotte Bird & Eddie Ungless) [proceedings]
AAAI/ACM Proceedings of AI, Ethics, Society (AIES); 2023

(14) Science in the Age of Large Language Models (with Abeba Birhane, David Leslie, Sandra Wachter) [journal]
Nature Reviews Physics, 2023

(13) In Conversation with Artificial Intelligence: Aligning Language Models with Human Values (with Iason Gabriel) [preprint, journal, blog]
Philosophy & Technology; 2023

(12) Reconciling Governmental Use of Online Targeting With Democracy (with Katia Andrić) [preprint, proceedings]
ACM Proceedings of Fairness, Accountability, and Transparency (FAccT); accepted 2023

(11) Taxonomy of Risks Posed by Language Models (with Laura Weidinger et al.). [preprint, preprint of a longer version, proceedings] 
ACM Proceedings of Fairness, Accountability, and Transparency (FAccT); 2022

(10) Algorithmic Fairness and Structural Injustice: Insights from Feminist Political Philosophy. [preprint, proceedings] 
AAAI/ACM Proceedings of AI, Ethics, Society (AIES); 2022

(9) Algorithmic and Human Decision-making: For a Double Standard of Transparency (with Mario Günther). [preprint, journal] 
AI & Society; 2022

(8) Counter Countermathematical Explanations. [preprint, journal]
Erkenntnis; 2022

(7) A New Role for Mathematics in Empirical Sciences. [preprint, journal]
Philosophy of Science; 2021

(6) Fairness and Data Protection Impact Assessments (with Damian Clifford). [proceedings] 
AAAI/ACM Proceedings of AI, Ethics, Society (AIES); 2021

(5) The Ethical Gravity Thesis: Marrian Levels & the Persistence of Algorithmic Bias in Automated Decision-making Systems (with Colin Klein). [preprint, proceedings, video] 
AAAI/ACM Proceedings of AI, Ethics, Society (AIES); 2021

(4) The Use and Misuse of Counterfactuals in Ethical Machine Learning (with Andrew Smart). [preprint,proceedings, video] 
ACM Proceedings of Fairness, Accountability, and Transparency (FAccT); 2021

Applied Mathematical and Algorithmic Decision-Making

(3) Airline Crew Scheduling: Models, Algorithms, and Datasets (with Mohammed Saddoune and François Soumis). [journal]
Euro Journal on Transportation and Logistics; 2017

(2) Simultaneous optimization of personalized intergrated recovery for pilots and copilots (with Saddoune et al.). [preprint]
Technical Report; 2015

(1) Simultaneous optimization of personalized intergrated scheduling (with Saddoune et al.) [preprint]
Technical Report; 2015

Reviews:

(ii) “Otavio Bueno and Steven French’s “Applying Mathematics: Immersion, Inference, Interpretations”. Philosophy of Science (with James R. Brown). [journal]

(i) “Scientific Collaboration and Collective Knowledge, Thomas Boyer-Kassem et al.” British Journal for the Philosophy of Science Review of Books. [preprint]

Talks

– Invited panelist “Large Language Models: Hype, Hope, Harm”, AAAI/ACM Conference on AI, Ethics, and Society (Aug 2023)

– Invited discussant Imperial College London, UK (June 2023)

– Invited speaker, Algorithmic Bias Workshop, University of Oxford, UK (June 2023)

– “Meaning and Large Language Models”, Philosophy of Deep Learning Conference, New York University, US (March 2023)

– “Value Alignment and Large Language Models”, Carnegie Mellon University, US (Mar 2023)

– “In Conversation with AI: Aligning Language Models with Human Values”, Philosophy, AI, and Society Workshop, Stanford University, US (Jan 2023)

– Invited Commentary on the book “Fairness and Machine Learning: Limitations and Opportunitie“, Stanford University, US (Jan 2023)

– Invited Talk “In Conversation with AI: Aligning Language Models with Human Values”, University of Eindhoven, Virtual (Jan 2023)

– TBD, Philosophy of Science Association (PSA), Pittsburgh, US (Nov 2022)

– Invited Talk “In Conversation with AI: Aligning Language Models with Human Values”, Ethics of AI workshop, University of Notre Dame Rome Global Gateway, Italy (Oct 2022)

– “Algorithmic Fairness and Structural Injustice: Insights from Feminist Political Philosophy”, Third International Rationality Summer Institute, Landau, Germany (July 2022)

– “Algorithmic Fairness and Structural Injustice: Insights from Feminist Political Philosophy”, Conference on AI, Ethics, and Society, University of Oxford, UK (Aug 2022)

– Invited Talk “In Conversation with AI: Aligning Language Models with Human Values”, Workshop on AI in Science, Cambridge-LMU, Germany (June 2022)

– Invited Talk “Applying Mathematics in the Computational World”, Conference on Mathematical Explanation, IHPST Paris, France (May 2022)

– Invited Talk “Algorithmic Fairness and Structural Injustice: Insights from Feminist Political Philosophy”, Workshop on Responsibility ans AI, University of Vienna, Austria (May 2022)

– Invited Talk “Algorithmic Fairness and Structural Injustice”, Philosophy Colloquium Series, Cornell University  (Apr 2022)

– Invited Talk “In Conversation with AI: Aligning Language Models with Human Values”, Invited Talk, Algorithmic Decision Making Conference, Aarhus University, Denmark (Mar 2022) 

– Invited Talk “Algorithmic Fairness and Structural Injustice: Insights from Feminist Political Philosophy”, Invited Talk, Scuola Superiore Sant’Anna di Pisa, Italy (Mar 2022)

– Invited panelist, Ethics and Artificial Intelligence at Conference on Neural Information Processing Systems (Dec 2021)

– Invited panelist, Technomoral conversations, University of Edinburgh (Dec 2021) 

– Invited panelist, Ethics expert meeting of the AI for safer children, United Nations (Dec 2021)

– “Kinds of Explanation in Machine Learning”, 27th Biennial Meeting of the Philosophy of Science Association, Baltimore, USA (Nov 2021) 

– “The Use and Misuse of Counterfactuals in Ethical Machine Learning”, 27th Biennial Meeting of the Philosophy of Science Association, Baltimore, USA (Nov 2021, poster)

– “Kinds of Explanation in Machine Learning”, Philosophy of Science Meets Machine Learning Workshop, University of Tübingen, Germany (Nov 2021) 

– “The Ethical Gravity Thesis: Marrian Levels and the Persistence of Bias in Automated Decision-making Systems”, Philosophy of Data Science Symposium, Upstate Workshop on AI and Human Values (Virtual, May 2021)

– “Counter Countermathematical Explanations”, Eastern APA Meeting, New York, USA (Virtual, Jan 2021)

– “Reasons, Values, Stakeholders: a Philosophical Framework for Explainable Artificial Intelligence”, Forms of Normativity: Transitions and Intersections Speaker Series, University of Vienna, Austria (Virtual, Dec 2020)

– “The Use and Misuse of Counterfactuals in Fair Machine Learning”, Workshop on Algorithmic Fairness through the Lens of Causality and Interpretability, NeurIPS, Vancouver, Canada (Dec 2020)

– “The Use and Misuse of Counterfactuals in Fair Machine Learning”, Workshop on Philosophy and Medical AI, University of Tübingen, Germany (Virtual, Oct 2020)

– “The Use and Misuse of Counterfactuals in Fair Machine Learning”, Bias and Fairness in AI Workshop at European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, Ghent, Belgium (with Andrew Smart, Virtual, Sep 2020)

– “Why and How Explanations Matter: Connecting Moral and Technical Dimensions of Algorithmic Decision-making”, Interpretable Machine Learning workshop, Simons Institute for the theory of computing, University of California Berkeley, USA (Virtual, July 2020) 

– “Why and How Explanations Matter: Connecting Moral and Technical Dimensions of Algorithmic Decision-making”, Athena in Action Workshop, Cornell University, USA (Virtual, June 2020)

– “Mathematical decisions and non-causal elements of explainable AI”, Workshop on Human-centric Machine Learning, NeurIPS, Vancouver, Canada (Dec 2019)

– “Mathematical and causal faces of explainable AI”, University of Washington Seattle, Department of Philosophy, USA (Nov 2019)

– “Mathematical and causal faces of explainable AI”, University of California San Diego, Department of Philosophy, USA (Nov 2019)

– “Mathematical and causal faces of explainable AI”, University of California Irvine, Department of Philosophy, USA (Nov 2019)

– “Mathematical and causal faces of explainable AI”, Stanford University, Department of Philosophy, USA (Oct 2019)

– “Levels and a new role for mathematics in empirical sciences”, British Society for the Philosophy of Science, Durham, UK (July 2019)

– “Levels and a new role for mathematics in empirical sciences”, Canadian Society for the History and Philosophy of Science, Vancouver, Canada (June 2019)

– “Can mathematics really make a difference?”,  Workshop on Non-causal Explanations: Logical, Linguistic, and Philosophical Perspectives, Ghent, Belgium (May 2019)

– “Can mathematics really make a difference?”, Workshop on Metaphysical Explanation in Science, Birmingham, UK (Jan 2019)

– “Computer simulations and the production of new pragmatic knowledge in social sciences”, 26th Biennial Meeting of the Philosophy of Science Association, Seattle, USA (Nov 2018) 

– “Auxiliary probabilities and the Principal Principle”,  9th European Congress of Analytic Philosophy, Munich, Germany (Aug 2017)

– “Non-causal and mathematics-based explanations”, Workshop on Causation, Explanation, and Conditionals, Tutzing & Munich, Germany (June 2017)

– “Computer simulations, mathematical models, and production of new knowledge”,  Canadian Society for the History and Philosophy of Science, Toronto, Canada (May 2017)

– “The explanatory role of mathematics in social sciences: the case of health economics”, 43rd Annual Philosophy of Science Conference, Dubrovnik, Croatia (April 2016)

– “An integrated simultaneous approach for pilots and copilots rescheduling problem”, Multidisciplinary International Scheduling Conference (MISTA), Prague, Czech Republic (Aug 2015)

– “An Integrated Simultaneous Approach for Pilots and Copilots Rescheduling Problem”, Joint International Meeting of Canadian Operational Research Society & Institute for Operations Research and the Management Sciences (INFORMS), Montreal, Canada (June 2015)

– “Simultaneous optimization of personalized integrated scheduling for pilots and copilots”, Institute for Operations Research and the Management Sciences (INFORMS) Annual Meeting, San Francisco, USA (Nov 2014)

– “Simultaneous optimization of personalized integrated scheduling for pilots and copilots”, Canadian Mathematical Society Women in Math, Banff International Research Center for Mathematical Innovation and Discovery, Banff, Canada (Oct 2014)

– ”Simultaneous optimization of personalized integrated scheduling for pilots and copilots”, Conference of the International Federation of Operational Research Societies (IFORS), Barcelona, Spain (July 2014)

– ”Simultaneous optimization of personalized integrated scheduling for pilots and copilots”, Optimization Days, Montreal, Canada (May 2014)

– ”Integrated personalized crew pairing and crew assignment problem”, 26th European Conference on Operational Research, Rome, Italy (July 2013)

– “Integrated personalized crew pairing and crew assignment problem”, Optimization Days, Montreal, Canada (May 2013)

– Artificial Intelligence and Democratic Values (LMU Munich, 2023)

– Ethics and Large Language Models (University of Cambridge, 2022)

– Fairness and Justice in Machine Learning  (Decision, Fairness, and Machine Learning, University of Bayreuth, Germany, 2022)

– Fairness in Machine Learning (Decision, Fairness, and Machine Learning, University of Bayreuth, Germany, 2020)

– Fair Decisions and Machine Learning (Research Methods, Australian National University, 2020, 2021)

– Introduction to Philosophy of Science (Research Methods, Australian National University, 2020, 2021)

– Ethics of Artificial Intelligence (Minds & Machines, University of Toronto, 2017)