MindDial: Belief Dynamics Tracking with Theory-of-Mind Modeling for Situated Neural Dialogue Generation
This work addresses the challenge of individual differences in contextual understanding for neural dialogue systems, offering an incremental improvement over existing models.
The paper tackles the problem of situated dialogue generation by proposing MindDial, a framework that models theory-of-mind to track beliefs and predict listener beliefs, resulting in higher task outcomes in scenarios involving common ground alignment and negotiation.
Humans talk in daily conversations while aligning and negotiating the expressed meanings or common ground. Despite the impressive conversational abilities of the large generative language models, they do not consider the individual differences in contextual understanding in a shared situated environment. In this work, we propose MindDial, a novel conversational framework that can generate situated free-form responses with theory-of-mind modeling. We introduce an explicit mind module that can track the speaker's belief and the speaker's prediction of the listener's belief. Then the next response is generated to resolve the belief difference and take task-related action. Our framework is applied to both prompting and fine-tuning-based models, and is evaluated across scenarios involving both common ground alignment and negotiation. Experiments show that models with mind modeling can achieve higher task outcomes when aligning and negotiating common ground. The ablation study further validates the three-level belief design can aggregate information and improve task outcomes in both cooperative and negotiating settings.