Development of a Trust-Aware User Simulator for Statistical Proactive Dialog Modeling in Human-AI Teams
This work addresses the problem of enhancing collaboration in human-AI teams through proactive dialog, but it is incremental as it builds on existing simulation methods for training and testing.
The paper tackled the challenge of designing proactive AI for human-AI teams by developing a corpus-based user simulator to train and test proactive dialog policies, with a task-step-based approach yielding better results due to improved modeling of sequential dependencies.
The concept of a Human-AI team has gained increasing attention in recent years. For effective collaboration between humans and AI teammates, proactivity is crucial for close coordination and effective communication. However, the design of adequate proactivity for AI-based systems to support humans is still an open question and a challenging topic. In this paper, we present the development of a corpus-based user simulator for training and testing proactive dialog policies. The simulator incorporates informed knowledge about proactive dialog and its effect on user trust and simulates user behavior and personal information, including socio-demographic features and personality traits. Two different simulation approaches were compared, and a task-step-based approach yielded better overall results due to enhanced modeling of sequential dependencies. This research presents a promising avenue for exploring and evaluating appropriate proactive strategies in a dialog game setting for improving Human-AI teams.