Creating explanations in collaborative human-machine knowledge exploration

The Transregional Collaborative Research Center (TRR 318) “Constructing Explainability” investigates how explanations of algorithmic decisions can be jointly constructed by the explainer and the explainee. The project C05 investigates how human decision makers and intelligent systems can collaboratively explore a decision problem to make a decision that is accountable and hence explainable. The goal is to model how both agents — the human and the AI — can contribute to constructing an explanation based on their respective knowledge. To this end, we investigate how human explanation dialogues proceed in order to derive principles of explanation generation and develop a system for collaborative knowledge exploration that combines large language models with cognitive modeling.