Explanations as Dialogues: Toward Human-Centered Conversational Explainable AI
For the Conversational User Interfaces (CUI) community, this work highlights a gap in current explainable AI research by emphasizing the conversational context of explanations.
The paper argues that explanations in AI should be studied as interactive dialogues rather than static artifacts, proposing a vision for Human-Centered Conversational XAI (HC2XAI) to improve effectiveness.
As AI systems become increasingly conversational, a gap emerges wherein explanations are studied as static artifacts, yet in practice, are experienced as dialogue. In this provocation, we argue that the conversational layer around an explanation is not incidental to its effectiveness, but a critical constituent. Drawing on three illustrative scenarios, we invite the CUI community to study explanations as interactive, conversational exchanges shaped by timing, tone, persona and conversational history, and introduce our vision for Human-Centered Conversational XAI (HC2XAI).