让大模型学会不同情绪，提升群体决策能力。
Enhancing Collective Intelligence in Large Language Models Through Emotional Integration
- 用情绪数据微调模型，模拟多样情绪响应。
- 15,064种角色配置下，情绪影响决策模式但保持准确率。
- 适合研究情感智能与群体认知的AI学者。
本研究探索将情绪多样性融入大型语言模型（LLMs）以增强集体智能。受人类群体智慧现象启发——群体决策常优于个体判断——我们使用Google的GoEmotions数据集和低秩适配（LoRA）对DarkIdol-Llama-3.1-8B模型进行微调，模拟情绪多样的回应。在法戈（北达科他州）与西雅图（华盛顿州）之间距离估算任务上，评估了15,064种独特人格配置下的表现，分析情绪状态与社会属性对决策的影响。结果表明，情绪整合改变了响应模式，同时维持了可接受的预测准确性，揭示其在增强人工集体智能方面的潜力。该研究为情绪多样性与决策之间的相互作用提供了洞见，指明了构建兼具情感深度与分析精度的智能系统路径。
原文摘要 · Abstract (English)
This research investigates the integration of emotional diversity into Large Language Models (LLMs) to enhance collective intelligence. Inspired by the human wisdom of crowds phenomenon, where group decisions often outperform individual judgments, we fine-tuned the DarkIdol-Llama-3.1-8B model using Google's GoEmotions dataset and Low-Rank Adaptation (LoRA) to simulate emotionally diverse responses. Evaluating the model on a distance estimation task between Fargo, ND, and Seattle, WA, across 15,064 unique persona configurations, we analyzed how emotional states and social attributes influence decision-making. Our findings demonstrate that emotional integration shapes response patterns while maintaining acceptable prediction accuracy, revealing its potential to enhance artificial collective intelligence. This study provides valuable insights into the interplay of emotional diversity and decision-making in LLMs, suggesting pathways for creating emotionally aware AI systems that balance emotional depth with analytical precision.
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。