Large Language Models (LLMs) can readily generate natural language explanations—or chain-of-thoughts (CoTs)—to justify their outputs. In this talk, I will first introduce methods for evaluating whether such explanations faithfully reflect the decision-making processes of the models that produce them. Second, I present the results of a user study involving 85 clinicians and medical students diagnosing chest X-rays. The study compares the effectiveness of natural language explanations, saliency maps, and their combination in supporting clinical decision-making.

Oana-Maria Camburu is an Assistant Professor in the Department of Computing at Imperial College London. She was a Principal Research Fellow in the Department of Computer Science at the University College London, where she held an Early Career Leverhulme Fellowship. She also did a postdoc at the University of Oxford, from which she obtained her PhD on Explaining Deep Neural Networks. Her main research interests lie in explainability, AI safety, and alignment.