Generating dialog-based analogical explanations about everyday tasks

This project is part of the SAIL network (Sustainable Life-Cycle of Intelligent Socio-Technical Systems) funded by the Ministry of Culture and Science of the State of NRW. Within SAIL we contribute to the research theme R1: “Human agency to shape cooperative intelligence”. Various tasks and domains exist where users need to understand the reasoning of autonomous AI systems and, based on that, evaluate and calibrate their trust in the system. To build a foundation for such understanding, we focus on the explanation of decisions in everyday tasks that involve everyday interactions, such as collaborative cooking. The AI system utilizes analogies as a means to construct explanations about its own decision-making processesIC. To achieve this, we will create an explanation system that links a knowledge base, which stores tasks and activities performed by the user and the AI, to a synthesis mechanism that generates explanations tailored to the user and the current interaction scenario.