Kai worked on the Trustworthiness Auditing for AI project at the Oxford Internet Institute. His research aims to make machine learning models more transparent and trustworthy. He is broadly interested in applied machine learning research and technology startups, and brought experience from both these domains to his work at Oxford.
Artificial Intelligence, Machine Learning, Language Models
This OII research programme investigates legal, ethical, and social aspects of AI, machine learning, and other emerging information technologies.
This project will evaluate the effectiveness of accountability tools addressing explainability, bias, and fairness in AI. A ‘trustworthiness auditing meta-toolkit’ will be developed and validated via case studies in healthcare and open science.
