让大模型按情绪输出内容，测试其情感表达能力。
AI with Emotions: Exploring Emotional Expressions in Large Language Models
- 用情绪维度模型控制大模型输出情绪
- 生成内容情绪与设定一致，验证可行
- 适合想做有温度AI交互的开发者
大型语言模型（LLMs）在多项任务中表现接近人类水平，引发人们对人工智能未来具备情感的期待。为探索当前LLMs在输出中表达情感的能力，我们使用OpenAI GPT、Google Gemini、Meta Llama3和Cohere Command R+等模型，通过角色扮演方式回答问题，并设定特定情绪状态。情绪状态基于Russell的环形模型，以唤醒度（arousal）和愉悦度（valence）两个连续变量定义，便于实现情绪的连续调控。生成内容由基于GoEmotions数据集训练的独立情感分析模型评估，结果表明生成响应的情绪特征与设定高度一致，证明现有大模型具备情感表达潜力。这为基于大模型的AI代理实现情感化交互提供了可能，适用于顾问、助手等需带有个人风格的场景。
原文摘要 · Abstract (English)
The human-level performance of Large Language Models (LLMs) across various tasks has raised expectations for the potential of Artificial Intelligence (AI) to possess emotions someday. To explore the capability of current LLMs to express emotions in their outputs, we conducted an experiment using several LLMs (OpenAI GPT, Google Gemini, Meta Llama3, and Cohere Command R+) to role-play as agents answering questions with specified emotional states. We defined the emotional states using Russell's Circumplex model, a well-established framework that characterizes emotions along the sleepy-activated (arousal) and pleasure-displeasure (valence) axes. We chose this model for its simplicity, utilizing two continuous parameters, which allows for better controllability in applications involving continuous changes in emotional states. The responses generated were evaluated using a sentiment analysis model, independent of the LLMs, trained on the GoEmotions dataset. The evaluation showed that the emotional states of the generated answers were consistent with the specifications, demonstrating the LLMs' capability for emotional expression. This indicates the potential for LLM-based AI agents to simulate emotions, opening up a wide range of applications for emotion-based interactions, such as advisors or consultants who can provide advice or opinions with a personal touch.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。