Towards Socially Intelligent Agents with Mental State Transition and Human Utility
This work addresses the problem of enhancing social intelligence in agents for applications like interactive games, though it is incremental as it builds on existing datasets and methods.
The paper tackles the challenge of building socially intelligent agents by incorporating mental state simulation and value modeling into dialogue agents, achieving state-of-the-art performance on prediction tasks in the LIGHT dataset.
Building a socially intelligent agent involves many challenges. One of which is to track the agent's mental state transition and teach the agent to make decisions guided by its value like a human. Towards this end, we propose to incorporate mental state simulation and value modeling into dialogue agents. First, we build a hybrid mental state parser that extracts information from both the dialogue and event observations and maintains a graphical representation of the agent's mind; Meanwhile, the transformer-based value model learns human preferences from the human value dataset, ValueNet. Empirical results show that the proposed model attains state-of-the-art performance on the dialogue/action/emotion prediction task in the fantasy text-adventure game dataset, LIGHT. We also show example cases to demonstrate: (i) how the proposed mental state parser can assist the agent's decision by grounding on the context like locations and objects, and (ii) how the value model can help the agent make decisions based on its personal priorities.