Sonja Kraiczy
E-mail: Sonja.Kraiczy [at] cs.ox.ac.uk
E-mail: Sonja.Kraiczy [at] cs.ox.ac.uk
on top of Mauna Kea, Hawaii
I’m a DPhil student in Computer Science at the University of Oxford, supervised by Edith Elkind and supported by an EPSRC scholarship. My research interests include computational social choice, algorithmic game theory, and mechanism design. I enjoy working on problems motivated by real-world applications as well as on foundational theoretical questions.
Currently, I am a Research Scientist Intern in the AI & Society group at Meta FAIR. In January 2027 I will be starting as a Assistant Research Professor at the Center for Data Science for Enterprise & Society at Cornell University.
Previously in 2025/2026, I worked part-time on a project on aggregating safety preferences within ARIA’s Safeguarded AI program, and part-time for Meta FAIR under Max Nickel on pluralistic alignment. In summer 2025 I participated in the PIBBSS research fellowship. I had the pleasure to visit Vince Conitzer and his gorup FOCAL at CMU in spring 25' and also shorter research visits with Piotr Skowron at the University of Warsaw and Piotr Faliszewski at the AGH Krakow.
Prior to my PhD, I completed an MSc in Mathematics and Foundations of Computer Science (MFoCS) at the University of Oxford, and a BSc (Hons) in Computing Science and Mathematics at the University of Glasgow.
Manuscripts
Sonja Kraiczy, Isaac Robinson, Edith Elkind
For Questions of Ought, AI could use some SAGE advice
Smitha Milliᵅ , Ratip Emin Berker, Sonja Kraiczy, Claudia Shi, Jack Kussman, Avinandan Bose, Edith Elkind, Himaghna Bhattacharjee, Ariel Procaccia, Maximilian Nickel
ICML 2026 Pluralistic Alignment Workshop
Publications
Where Should Society Draw the Line? A Social Choice Approach to Collective Consent
Chris Dongᵅ, Sonja Kraiczy, Rohit Vasishta, Markus Brill, Wesley H. Holliday, Niclas Boehmer
NeurIPS 2026
Social Choice Foundations for Simulation-Augmented Generation
Sonja Kraiczyᵅ , Smitha Milliᵅ , Ratip Emin Berker, Avinandan Bose, Brandon Amos, Jamelle Watson-Daniels, Maximilian Nickel, Edith Elkind, and Ariel D. Procaccia
NeurIPS 2026
Proportional Committee Elections with Positive and Negative Votes
Sonja Kraiczy*, Georgios Papasotiropoulos, Grzegorz Pierczyński, Piotr Skowron
EC 2026
Enforcing Axioms for AI Alignment under Loss-Based Rules
Alexandros Hollender* , Sonja Kraiczy
ICLR 2026
A Lower Bound for Local Search PAV
Sonja Kraiczy, Edith Elkind
ESA 2024
Stability in Random Hedonic Games
Martin Bullinger, Sonja Kraiczy*
EC 2024, [COMSOC Video Seminar]
An Adaptive and Verifiably Proportional Method for Participatory Budgeting
Sonja Kraiczy, Edith Elkind
WINE 2023
Properties of the Mallows Model Depending on the Number of Alternatives:
A Warning for an Experimentalist
Niclas Boehmer, Piotr Faliszewski, Sonja Kraiczy*
ICML 2023
Fairness in Temporal Slot Assignment
Edith Elkind, Sonja Kraiczy*, Nicholas Teh
SAGT 2022
Explaining Preferences by Multiple Patterns in Voters' Behavior
Sonja Kraiczy, Edith Elkind
IJCAI 2022.
Exact Learning of Preference Structure: Single-peaked Preferences and Beyond
Sonja Kraiczy, Edith Elkind
ICML 2022
Sonja Kraiczy*, Ciaran McCreesh
IJCAI 2021
On Absolutely and Simply Popular Rankings
Sonja Kraiczy, Agnes Cseh and David Manlove
(Extended Abstract)] AAMAS 2021
Discrete Applied Mathematics 2023
*alphabetical ordering of author names (typical in collaborations in social choice)
ᵅ lead author (typical in collaborations in AI)