Does Your AI Agent Get You? A Personalizable Framework for Approximating Human Models from Argumentation-based Dialogue Traces
This addresses the need for personalized AI interactions in explainable AI, though it is incremental as it builds on existing argumentation methods.
The paper tackles the problem of AI agents using predetermined human models in argumentation-based dialogues by introducing Persona, a framework that dynamically learns and updates human models during interactions. The result shows that Persona effectively captures evolving human beliefs and outperforms state-of-the-art methods in empirical evaluations.
Explainable AI is increasingly employing argumentation methods to facilitate interactive explanations between AI agents and human users. While existing approaches typically rely on predetermined human user models, there remains a critical gap in dynamically learning and updating these models during interactions. In this paper, we present a framework that enables AI agents to adapt their understanding of human users through argumentation-based dialogues. Our approach, called Persona, draws on prospect theory and integrates a probability weighting function with a Bayesian belief update mechanism that refines a probability distribution over possible human models based on exchanged arguments. Through empirical evaluations with human users in an applied argumentation setting, we demonstrate that Persona effectively captures evolving human beliefs, facilitates personalized interactions, and outperforms state-of-the-art methods.