A Grounded Interaction Protocol for Explainable Artificial Intelligence
By Prashan Madumal, Tim Miller, Liz Sonenberg, Frank Vetere. 2019
105 citations recorded by the source corpus.
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.
Subfields: Artificial Intelligence
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Q. Liao
- Longo Luca
- Giulia Vilone
- Kush R. Varshney
- Tim Miller
- Liz Sonenberg
- Prashan Madumal
- Frank Vetere
Citations in the corpus
- Explainable Artificial Intelligence: a Systematic Review (2020, background): “On one hand, [81] grounded this three-stage formal protocol on the data collected from almost four hundred real dialogues which were examined to detect the key components of an explanation, the relationships between them and their order of occurrence.”
- Questioning the AI: Informing Design Practices for Explainable AI User Experiences (2020, background): “We work towards these goals in the next section.”
- A Study of Automatic Metrics for the Evaluation of Natural Language Explanations (2021, background): “Explanations are a core component of human interaction (Scalise et al., 2017; Krening et al., 2017; Madumal et al., 2019).”
- Human-Centered Explainable AI (XAI): From Algorithms to User Experiences (2021, background): “These theories offer appealing grounds to build computational models, and recent XAI has begun to explore dialogue models for interactive XAI [71].”
- Explainable Reinforcement Learning Through a Causal Lens (2019, background): “Although some recent work has emphasized the importance of causal explanation for explainable AI systems (Miller 2018b; 2018a; Madumal et al. 2019; Madumal 2019), work on generating explanations from causal explanation models for MDPs and RL agents have been absent.”