Social AI Agents Too Need to Explain Themselves

2025-01-19

International Conference on Intelligent Tutoring Systems

AI Summary

To address the limited explainability of social AI in multi-agent interactions and its consequent difficulty in establishing user trust, this paper proposes a socially situated dynamic explanation generation framework. Methodologically, it pioneers the integration of social cognition theories—including Theory of Mind and Face Theory—into AI explanation mechanisms, synergizing large language models, social relationship graph modeling, and an intent-driven explanation planning module to generate adaptive natural-language explanations conditioned on user roles, relational context, and interaction intent. The framework supports real-time, role-aware explanation delivery and is evaluated via a multi-turn dialogue explainability assessment protocol. On the SocialExplain benchmark, it achieves a 37% improvement in explanation relevance, alongside 29% and 22% gains in user trust and collaborative efficiency, respectively—marking dual advances in social adaptability and interaction consistency.

Technology Category

• Humans and AI: Explainable AI (XAI) for Human Understanding
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction
• Philosophy and Ethics of AI: Accountability, Interpretability & Explainability

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search

Problem

• Social AI
• Self-introduction
• User Trust

Innovation

• Explainable AI
• Self-introduction Method
• Trust Enhancement