A dialog-based approach to explaining machine-learning models (B01)

• Subject Area: Image and Language Processing, Computer Graphics and Visualisation, Human Computer Interaction, Ubiquitous and Wearable Computing ; Empirical Social Research ; Methods in Artificial Intelligence and Machine Learning ; Communication Sciences
• Term: since 2021
• Project identifier: Deutsche Forschungsgemeinschaft (DFG) - Project number 438445824

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.

• DFG Programme: CRC/Transregios
• Subproject of: TRR 318: Constructing explainability
• Applicant Institution: Universität Paderborn
• Project Heads: Professor Dr. Philipp Cimiano; Professorin Dr. Elena Esposito; Professor Dr. Axel-Cyrille Ngonga Ngomo, until 12/2025