PhD Position on Safety in Conversational AI

We are looking for a PhD candidate to join the Dialogue Modelling Group at the ILLC as part of the LESSEN consortium funded by the Dutch Research Council (NWO). LESSEN aims to develop, implement and evaluate safe and transparent conversational AI agents based on state-of-the-art neural architectures. The focus is on lesser resourced tasks, domains, and scenarios. This PhD project (PhD 9 within LESSEN) will investigate new methods for preventing the generation of unsafe utterances using interpretability and controlled text generation tecniques. Candidates will be pre-selected through the ELLIS PhD Program (application deadline: 15 November 2022). If you are interested in this position, please mention this explicitly in the motivation letter when applying through the ELLIS portal. A formal UvA vacancy ad will be available in due time.