Structures Underlying Explanations
摘要
This chapter presents recurring structures of interactions – and their associated goals – as they occur in explaining processes. It explores how explanations are not delivered in isolation but unfold through dynamic, structured sequences of interaction between participants. Beginning with the smallest units, we examine how individual dialog acts and multimodal signals form micro-patterns within turns. These, in turn, compose meso-level structures such as pragmatic frames that organize sequences of interaction into meaningful, goal-oriented episodes. At the macro-level, we identify common types of explanatory dialogs, such as inquiry, information-seeking, or deliberation, which are shaped by participants’ goals and situational demands. The chapter highlights how these patterns of structure are instantiated differently across social and situational contexts and proposes that understanding them is crucial for designing socially intelligent and adaptive XAI systems. By analyzing how these structures emerge and function, we offer a framework for operationalizing explanation structures in a way that supports co-constructive and context-sensitive human-AI interaction.