An Explanation-oriented Inquiry Dialogue Game for Expert Collaborative Recommendations

TL;DR

This paper introduces an explanation-oriented inquiry dialogue game designed for medical experts to collaboratively make recommendations, enhancing explainability and traceability of reasoning in multiagent systems.

Contribution

It develops a novel dialogue game framework incorporating explanation-based forces, and demonstrates its effectiveness through a prototype and user study with medical experts.

Findings

The dialogue game supports collaborative recommendations among medical experts.

The prototype was positively evaluated in a formative user study.

The system provides rich reasoning traces and enhances communication.

Abstract

This work presents a requirement analysis for collaborative dialogues among medical experts and an inquiry dialogue game based on this analysis for incorporating explainability into multiagent system design. The game allows experts with different knowledge bases to collaboratively make recommendations while generating rich traces of the reasoning process through combining explanation-based illocutionary forces in an inquiry dialogue. The dialogue game was implemented as a prototype web-application and evaluated against the specification through a formative user study. The user study confirms that the dialogue game meets the needs for collaboration among medical experts. It also provides insights on the real-life value of dialogue-based communication tools for the medical community.