Desiree is a DPhil (PhD) student in Computer Science and Doctoral Scholar at the Institute for Ethics in AI, supervised by Professor Sir Nigel Shadbolt (Chair of AI@Oxford Research). Her research is in technical AI safety and alignment. Desiree's current work focuses on constitutional midtraining, generously funded by BlueDot Impact. Another recent project of hers was on diverse reward model ensembles, winning first place in Research Impact Oxford.
Desiree’s background is in human-centred computing and natural language processing. Before this PhD, she completed her Master of Science at the University of Oxford, graduating with Distinction in her degree and thesis. Her thesis was on recommender system alignment, where she built an NLP pipeline to measure the alignment between recommendations and user behaviour. She has also published at leading human-centred computing venues, namely ACM CHI and the International Journal of Human-Computer Studies, the latter of which published her Bachelor's dissertation.
Beyond research, Desiree is actively involved in the AI safety and broader computer science community. She serves on the committees of Oxford Womxn in Computer Science and OxAI Safety and Governance, and has helped organise the Oxford Human-AI Workshop 2024.
Please follow Desiree on LinkedIn for her most recent updates.