Improving Dialog Systems for Negotiation with Personality Modeling

TL;DR

This paper introduces a probabilistic theory of mind approach to model and infer opponents' personalities in negotiation dialog systems, improving agreement rates and enabling diverse behaviors.

Contribution

It presents a novel probabilistic framework for incorporating opponent personality modeling into negotiation dialog agents, enhancing adaptability and performance.

Findings

20% higher dialog agreement rate with ToM inference

Model exhibits diverse negotiation behaviors

Effective in mixed opponent populations

Abstract

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.