An Explanation-oriented Inquiry Dialogue Game for Expert Collaborative Recommendations
Qurat-ul-ain Shaheen, Katarzyna Budzynska, Carles Sierra
TL;DR
This paper tackles the challenge of enabling explainable, expert-level collaboration in medicine by proposing the Experts' Dialogue Game (EDG), a formal inquiry-dialogue that embeds explanation-based illocutionary forces to produce rich traces of reasoning. It provides a requirements-driven specification (Agent, Cooperation, Protocol, and Implementation) derived from medical practice, then formalizes EDG with a detailed typology of locutions and rules, plus a prototype web platform enforcing the protocol. A formative user study with medical students evaluates usability and gathers qualitative insights, supporting the feasibility and perceived value of EDG for multidisciplinary discussion and knowledge transfer. The work highlights a methodological stance of applying software-engineering practices to formal dialogue systems and points to future work on runtime properties, scalability, and open-source deployment to advance explainable, collaborative healthcare decision-making.
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.