A Grounded Interaction Protocol for Explainable Artificial Intelligence
This work addresses the problem of improving human-AI interaction for explainability, though it is incremental as it builds on existing dialogue frameworks.
The paper tackled the challenge of meaningful interaction in explainable AI by proposing a grounded interaction protocol derived from 398 explanation dialogues, and evaluation with 101 human-agent dialogues showed it closely follows real conversations.
Explainable Artificial Intelligence (XAI) systems need to include an explanation model to communicate the internal decisions, behaviours and actions to the interacting humans. Successful explanation involves both cognitive and social processes. In this paper we focus on the challenge of meaningful interaction between an explainer and an explainee and investigate the structural aspects of an interactive explanation to propose an interaction protocol. We follow a bottom-up approach to derive the model by analysing transcripts of different explanation dialogue types with 398 explanation dialogues. We use grounded theory to code and identify key components of an explanation dialogue. We formalize the model using the agent dialogue framework (ADF) as a new dialogue type and then evaluate it in a human-agent interaction study with 101 dialogues from 14 participants. Our results show that the proposed model can closely follow the explanation dialogues of human-agent conversations.