通过情感整合增强大型语言模型中的集体智能
Enhancing Collective Intelligence in Large Language Models Through Emotional Integration
AI总结：
本研究通过 GoEmotions 数据集和 LoRA 微调 DarkIdol-Llama-3.1-8B 模型以整合情感多样性，验证了情感整合能在保持预测精度的同时塑造响应模式，从而有效增强大型语言模型的集体智能。
摘要：
本研究探讨了将情感多样性整合到大型语言模型（LLMs）中以增强集体智能。受群体决策往往优于个体判断的人类群体智慧现象启发，我们使用 Google 的 GoEmotions 数据集和低秩适应（LoRA）对 DarkIdol-Llama-3.1-8B 模型进行微调，以模拟情感多样的响应。在针对 Fargo, ND 与 Seattle, WA 之间的距离估计任务上，跨越 15,064 种独特的人物角色配置对该模型进行评估，我们分析了情感状态和社会属性如何影响决策。研究结果表明，情感整合在保持可接受预测精度的同时塑造了响应模式，揭示了其增强人工集体智能的潜力。本研究为 LLMs 中情感多样性与决策的相互作用提供了宝贵见解，为创建平衡情感深度与分析精度的情感感知 AI 系统指明了路径。
英文摘要：
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.
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。
