TRR 318-2 - Project B01: A dialog-based approach to explaining machine-learning models

B01 explores how dialog-based explanations of machine learning (ML) models function in real-world organizational contexts, accounting for organizational structures, roles, and communication styles, focusing on the predictive policing domain. An experimental evaluation showed that dialog-based explanations significantly enhance users’ understanding compared to static ones. In its second phase, the project will develop a modular multi-agent hybrid dialogue architecture to support enhanced monitoring and thus adaptation of the explanation to the specific needs of the user.