Sotabase

Career

· Advisor, Centre for Data Ethics and Innovation (CDEI)2025–
· Advisor, Centre for Science and Policy (CSaP)2025–
· Advisor, Centre for the Study of Existential Risk (CSER)2025–
· Director of Research in Machine Learning, University of Cambridge2014–
· Programme Director for Trust and Society, Leverhulme Centre for the Future of Intelligence
· Head of Safe and Ethical AI, The Alan Turing Institute

Publications (189)

Rethinking Attention with Performers
International Conference on Learning Representations · 2020
2,027
cited
Explainable machine learning in deployment
FAT* · 2019
654
cited
MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models
International Conference on Learning Representations · 2023
565
cited
Accountability of AI Under the Law: The Role of Explanation
arXiv.org · 2017
473
cited
Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims
arXiv.org · 2020
424
cited
Concrete Problems for Autonomous Vehicle Safety: Advantages of Bayesian Deep Learning
International Joint Conference on Artificial Intelligence · 2017
334
cited
Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertainty
AAAI/ACM Conference on AI, Ethics, and Society · 2020
291
cited
A Unified Approach to Quantifying Algorithmic Unfairness: Measuring Individual &Group Unfairness via Inequality Indices
Knowledge Discovery and Data Mining · 2018
287
cited
Evaluating and Aggregating Feature-based Model Explanations
International Joint Conference on Artificial Intelligence · 2020
273
cited
Human Perceptions of Fairness in Algorithmic Decision Making: A Case Study of Criminal Risk Prediction
The Web Conference · 2018
240
cited
Leveraging Data Science to Combat COVID-19: A Comprehensive Review
IEEE Transactions on Artificial Intelligence · 2020
237
cited
Beyond Distributive Fairness in Algorithmic Decision Making: Feature Selection for Procedurally Fair Learning
AAAI Conference on Artificial Intelligence · 2018
232
cited
The Case for Process Fairness in Learning: Feature Selection for Fair Decision Making
2016
228
cited
Controlling Text-to-Image Diffusion by Orthogonal Finetuning
Neural Information Processing Systems · 2023
220
cited
From Parity to Preference-based Notions of Fairness in Classification
Neural Information Processing Systems · 2017
218
cited
Harms from Increasingly Agentic Algorithmic Systems
Conference on Fairness, Accountability and Transparency · 2023
198
cited
Synthetic Data - what, why and how?
arXiv.org · 2022
169
cited
Transparency: Motivations and Challenges
Explainable AI · 2019
165
cited
Blind Justice: Fairness with Encrypted Sensitive Attributes
International Conference on Machine Learning · 2018
161
cited
Structured Evolution with Compact Architectures for Scalable Policy Optimization
International Conference on Machine Learning · 2018
160
cited
Sotabase