An Explanation-oriented Inquiry Dialogue Game for Expert Collaborative Recommendations

2025-11-03

AI Summary

To address insufficient explainability in interdisciplinary collaboration among medical experts, this paper proposes a multi-agent collaborative recommendation framework grounded in inquiry-based dialogue. Methodologically, it innovatively embeds explanatory illocutionary acts into formalized dialogue protocols, establishing a game-theoretic dialogue mechanism that supports multi-role knowledge integration, and implements a web-based prototype system with traceable reasoning trajectories. The primary contributions are: (1) the first realization of collaborative reasoning in medical multi-agent systems that simultaneously ensures process transparency and cognitive interpretability; and (2) empirical validation through formative user studies demonstrating significant improvements in expert consensus-building efficiency and explanation satisfaction—indicating strong practical potential as a clinical decision support tool.

Technology Category

• Multiagent Systems: Agreement, Argumentation & Negotiation
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy

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.

Problem

• Developing collaborative dialogue system for medical expert recommendations
• Incorporating explainability into multiagent reasoning processes
• Enabling knowledge integration through explanation-based inquiry dialogues

Innovation

• Inquiry dialogue game integrates explanation-based illocutionary forces
• Web-application prototype enables collaborative expert recommendations
• System generates reasoning traces through multiagent dialogue interactions