Lujain Ibrahim

about // research // news // contact

Hi! I'm currently completing a PhD in Social Data Science at the University of Oxford. My research focuses on sociotechnical approaches to evaluating and governing AI systems, their impact, and risks to society. My doctoral thesis specifically investigates how human-AI interaction complicates safety evaluation of general-purpose AI systems (see research).

My background is in computer engineering and international relations. I completed my Master's degree in international relations at Tsinghua University in Beijing as a Schwarzman Scholar. My undergraduate degree is in computer engineering from New York University (NYU), Abu Dhabi. Over the years, I've been a fellow at Centre for Governance of AI, Digital Asia Hub, and The Montreal AI Ethics Institute. My extended list of engagements can be found here.

Outside of research, I do creative coding work that demystifies emerging technologies, like the ones I build and study, to the public at large. With the support of The Mozilla Foundation, I recently co-built "The Algorithm", a web game that breaks down how recommendation algorithms work (and don't work) to a non-expert audience. My public-facing work was recently highlighted by The Webby Awards and Omidyar Network in their latest Responsible Tech Industry Report.


My research approach is grounded in information theory and human-centered computing, but also draws on cognitive science and design studies. I directly work with both models and people, aiming to evaluate and enhance their interactions by developing and testing frameworks, as well as conducting experiments and user studies. My publications can be found here.


* [May 2024] Started internship with Google DeepMind's Ethics Research Team, working on model safety evaluation

* [May 2024] New preprint on human interaction evaluations for LLM safety, risks, and harms

* [Apr 2024] New preprint on harms from AI user interface designs, presented in CHI 2024 Workshop on Human-centered Evaluation and Auditing of Language Models

* [Feb 2024] Launched "The Algorithm" - a web-based game explainer of recommendation systems

* [Jan 2024] Joined Centre for Governance of AI as a winter research fellow to work on contextually-relevant model safety evaluations

* [Dec 2024] New preprint on the persuasiveness of role-playing large language models

* [Nov 2023] Awarded Dieter Schwarz Foundation-OII grant for research on AI, Government and Policy

* [Nov 2023] Presented work-in-progress game at International Documentary Film Festival of Amsterdam DocLab


If we have similar research interests and think we can work together, please reach out!  lujainmibrahim  lujainibrahim

about // research // news // contact