arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.01633cs.MAcs.AIcs.CLcs.CY
收藏

社会模拟智能体中的自我情绪融合对话生成

Self-Emotion Blended Dialogue Generation in Social Simulation Agents

The University of Tokyo（东京大学）；Couger Inc（库格公司）

Qiang Zhang, Jason Naradowsky, Yusuke Miyao

备注：
Accepted in SIGDIAL 2024
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文研究 LLM 社会模拟智能体的自我情绪，通过策略预测、微调模型评估和多主题虚拟讨论实验，证明其可提升对话拟人度与自然性，并显著改变约半数决策。

摘要：

在参与对话时，虚拟模拟环境中的对话智能体可能会表现出与即时对话情境无关的自身情绪状态，这一现象被称为自我情绪。本研究探讨在大型语言模型（LLM）驱动的模拟框架中，此类自我情绪如何影响智能体在对话策略和决策方面的行为。在一项对话策略预测实验中，我们分析了智能体在具有和不具有自我情绪两种情况下所采用的对话策略选择，并将其与人类的选择进行比较。结果表明，纳入自我情绪有助于智能体展现出更接近人类的对话策略。在另一项独立实验中，我们比较了在 GPT-4 生成的对话数据集上微调的模型性能，证明自我情绪能够带来更好的整体自然性和拟人感。最后，在一个智能体围绕多个主题展开讨论的虚拟模拟环境中，我们表明智能体的自我情绪能够显著影响其决策过程，导致约 50% 的决策发生变化。

英文摘要：

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.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑