用多智能体系统帮用户过滤情绪化信息，冷静决策不丢失原意。
Multi-Agent Large Language Model Based Emotional Detoxification Through Personalized Intensity Control for Consumer Protection
- 四智能体协作：分析情绪、重写文本、监控习惯、推荐模式
- 降低情绪刺激19.3%，保持原文语义几乎不变
- 适合易受情绪影响的用户，尤其新闻类内容
在注意力经济中，煽动性内容使消费者长期处于高强度情绪刺激下，影响理性判断。本文提出基于多智能体大语言模型的情绪净化系统MALLET，包含四个模块：情绪分析、情绪调节、平衡监控和个性化引导。情绪分析模块使用六类情绪BERT分类器量化刺激强度；情绪调节模块通过大模型将文本重写为中性（BALANCED）或补充中性（COOL）两种模式；平衡监控模块分析每周信息消费模式并生成个性化建议；个性化引导模块根据用户敏感度推荐呈现方式。在800篇AG News文章上的实验表明，情绪刺激得分最高降低19.3%，情绪平衡显著提升，且刺激降低与语义保留近零相关，说明二者可独立控制。类别分析显示体育、商业、科技类情绪刺激下降17.8%至33.8%，而世界类因事实本身高刺激，效果有限。该系统为用户冷静接收信息提供无损方案。
原文摘要 · Abstract (English)
In the attention economy, sensational content exposes consumers to excessive emotional stimulation, hindering calm decision-making. This study proposes Multi-Agent LLM-based Emotional deToxification (MALLET), a multi-agent information sanitization system consisting of four agents: Emotion Analysis, Emotion Adjustment, Balance Monitoring, and Personal Guide. The Emotion Analysis Agent quantifies stimulus intensity using a 6-emotion BERT classifier, and the Emotion Adjustment Agent rewrites texts into two presentation modes, BALANCED (neutralized text) and COOL (neutralized text + supplementary text), using an LLM. The Balance Monitoring Agent aggregates weekly information consumption patterns and generates personalized advice, while the Personal Guide Agent recommends a presentation mode according to consumer sensitivity. Experiments on 800 AG News articles demonstrated significant stimulus score reduction (up to 19.3%) and improved emotion balance while maintaining semantic preservation. Near-zero correlation between stimulus reduction and semantic preservation confirmed that the two are independently controllable. Category-level analysis revealed substantial reduction (17.8-33.8%) in Sports, Business, and Sci/Tech, whereas the effect was limited in the World category, where facts themselves are inherently high-stimulus. The proposed system provides a framework for supporting calm information reception of consumers without restricting access to the original text.
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。