Does Your AI Agent Get You? a Personalizable Framework for Approximating Human Models from Argumentation-Based Dialogue Traces
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.
Cite
Text
Tang et al. "Does Your AI Agent Get You? a Personalizable Framework for Approximating Human Models from Argumentation-Based Dialogue Traces." AAAI Conference on Artificial Intelligence, 2025. doi:10.1609/AAAI.V39I13.33578Markdown
[Tang et al. "Does Your AI Agent Get You? a Personalizable Framework for Approximating Human Models from Argumentation-Based Dialogue Traces." AAAI Conference on Artificial Intelligence, 2025.](https://mlanthology.org/aaai/2025/tang2025aaai-your/) doi:10.1609/AAAI.V39I13.33578BibTeX
@inproceedings{tang2025aaai-your,
title = {{Does Your AI Agent Get You? a Personalizable Framework for Approximating Human Models from Argumentation-Based Dialogue Traces}},
author = {Tang, Yinxu and Vasileiou, Stylianos Loukas and Yeoh, William},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2025},
pages = {14405-14413},
doi = {10.1609/AAAI.V39I13.33578},
url = {https://mlanthology.org/aaai/2025/tang2025aaai-your/}
}