Self-Emotion Blended Dialogue Generation in Social Simulation Agents
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916345858228224 |
|---|---|
| author | Zhang, Qiang Naradowsky, Jason Miyao, Yusuke |
| author_facet | Zhang, Qiang Naradowsky, Jason Miyao, Yusuke |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_01633 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Self-Emotion Blended Dialogue Generation in Social Simulation Agents Zhang, Qiang Naradowsky, Jason Miyao, Yusuke Multiagent Systems Artificial Intelligence Computation and Language Computers and Society I.2.7; I.2; I.6 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. |
| title | Self-Emotion Blended Dialogue Generation in Social Simulation Agents |
| topic | Multiagent Systems Artificial Intelligence Computation and Language Computers and Society I.2.7; I.2; I.6 |
| url | https://arxiv.org/abs/2408.01633 |