Does Your AI Agent Get You? A Personalizable Framework for Approximating Human Models from Argumentation-based Dialogue Traces

TL;DR

This paper introduces Persona, a framework that allows AI agents to dynamically learn and adapt to human models during argumentation dialogues, improving personalized interactions and understanding of human beliefs.

Contribution

The paper presents a novel framework combining prospect theory, probability weighting, and Bayesian updates to dynamically model human users in argumentation-based AI systems.

Findings

Persona effectively captures evolving human beliefs.

It enables personalized and adaptive AI-human interactions.

Outperforms existing methods in empirical evaluations.

Abstract

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.