Self-Emotion Blended Dialogue Generation in Social Simulation Agents
This addresses the challenge of making social simulation agents more realistic for applications in virtual environments, though it is incremental as it builds on existing LLM frameworks.
This study tackled the problem of how self-emotion in dialogue agents affects their behaviors in a large language model-driven simulation, finding that incorporating self-emotion leads to more human-like dialogue strategies, better naturalness and humanness, and approximately a 50% change in decision-making.
When engaging in conversations, dialogue agents in a virtual simulation environment may exhibit their own emotional states that are unrelated to the immediate conversational context, a phenomenon known as self-emotion. This study explores how such self-emotion affects the agents' behaviors in dialogue strategies and decision-making within a large language model (LLM)-driven simulation framework. In a dialogue strategy prediction experiment, we analyze the dialogue strategy choices employed by agents both with and without self-emotion, comparing them to those of humans. The results show that incorporating self-emotion helps agents exhibit more human-like dialogue strategies. In an independent experiment comparing the performance of models fine-tuned on GPT-4 generated dialogue datasets, we demonstrate that self-emotion can lead to better overall naturalness and humanness. Finally, in a virtual simulation environment where agents have discussions on multiple topics, we show that self-emotion of agents can significantly influence the decision-making process of the agents, leading to approximately a 50% change in decisions.