Tell me more: Intent Fulfilment Framework for Enhancing User Experiences in Conversational XAI

One explanation is never enough: The research demonstrates that different users need different types of explanations to understand AI decisions. The paper's Intent Fulfilment Framework shows that combining multiple explanation types—rather than providing a single explanation—significantly improves user engagement and understanding of how AI systems work.

Follow-up conversations matter for trust: A key finding is that users need the ability to ask follow-up questions about explanations to verify accuracy, seek clarification, or explore alternative explanations. This conversational back-and-forth is essential for users to feel confident they truly understand why an AI made a particular decision.

Explanation experiences are personal: The research emphasizes that how people experience and understand AI explanations is subjective and user-centered. This means responsible AI systems should be designed to adapt to individual user needs rather than applying a one-size-fits-all approach to transparency.

Conversational interfaces improve XAI outcomes: The study's comparative user testing showed that a dialogue-based system for exploring explanations improved user engagement, perceived system utility, and overall user experience compared to static explanation approaches, suggesting conversational AI is a practical tool for responsible AI deployment.

Responsible AI requires iterative design: The framework reinforces that creating trustworthy AI systems demands ongoing interaction between users and explanations, not just providing information upfront—organizations should build systems that allow users to actively explore and question AI decision-making.