Self-Emotion Blended Dialogue Generation in Social Simulation Agents

Qiang Zhang, Jason Naradowsky, Yusuke Miyao

Abstract
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 free discussions, 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.
Anthology ID:
2024.sigdial-1.21
Volume:
Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue
Month:
September
Year:
2024
Address:
Kyoto, Japan
Editors:
Tatsuya Kawahara, Vera Demberg, Stefan Ultes, Koji Inoue, Shikib Mehri, David Howcroft, Kazunori Komatani
Venue:
SIGDIAL
SIG:
SIGDIAL
Publisher:
Association for Computational Linguistics
Note:
Pages:
228–247
Language:
URL:
https://aclanthology.org/2024.sigdial-1.21
DOI:
10.18653/v1/2024.sigdial-1.21
Bibkey:
Cite (ACL):
Qiang Zhang, Jason Naradowsky, and Yusuke Miyao. 2024. Self-Emotion Blended Dialogue Generation in Social Simulation Agents. In Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 228–247, Kyoto, Japan. Association for Computational Linguistics.
Cite (Informal):
Self-Emotion Blended Dialogue Generation in Social Simulation Agents (Zhang et al., SIGDIAL 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/dois-2013-emnlp/2024.sigdial-1.21.pdf
PDF Search