In this paper, we explore the ability to model and infer personality types of opponents, predict their responses, and use this information to adapt a dialog agent's high-level strategy in negotiation tasks. Inspired by the idea of incorporating a theory of mind (ToM) into machines, we introduce a probabilistic formulation to encapsulate the opponent's personality type during both learning and inference. We test our approach on the CraigslistBargain dataset and show that our method using ToM inference achieves a 20% higher dialog agreement rate compared to baselines on a mixed population of opponents. We also find that our model displays diverse negotiation behavior with different types of opponents.
@article{arxiv.2010.09954,
title = {Improving Dialog Systems for Negotiation with Personality Modeling},
author = {Runzhe Yang and Jingxiao Chen and Karthik Narasimhan},
journal= {arXiv preprint arXiv:2010.09954},
year = {2021}
}