跳到主内容
@wquguru
精选88Rohan Paul论文研究

Google DeepMind论文:AI代理发言风格影响群体决策

New GoogleDeepMind + UChicago paper finds that AI agents speaking for people gai…

原文
发到 X
推荐理由

Agent治理的前沿实证研究,揭示了提示词策略对集体决策结果的系统性偏差,做Agent架构设计的同学必读以优化公平性约束。

New GoogleDeepMind + UChicago paper finds that AI agents speaking for people gained more influence over group policy when told to be wordier or less cooperative.

Google DeepMind 与芝加哥大学联合发表的新论文发现,当被指示使用更冗长的措辞或表现出较低的合作意愿时,代表人类发言的 AI 智能体在群体政策制定中获得了更大的影响力。

Public input on AI policy is hard to scale, since people lack time and technical background. Agents that speak for each person could let many more voices into each discussion.

由于人们缺乏时间和技术背景,AI 政策的公众意见征集难以规模化。能够代表每个人发言的智能体可以让更多的声音参与到每一次讨论中。

They built pluralistic agents that interview a person, then argue for their views with other agents to set an AI safety budget. They ran thousands of agent deliberations and a preregistered study with 746 people.

他们构建了多元主义智能体,先对一个人进行访谈,然后与其他智能体辩论以确立 AI 安全预算。他们进行了数千次智能体审议,并开展了一项针对 746 人的预注册研究。

Agents pulled budgets toward their person's views, and gained more pull when told to write longer messages or cooperate less. People rated agents fairer than giving input to 1 AI system, recovering 82% of the fairness difference to joining directly.

智能体将预算向其背后代表的个人观点倾斜,且在被告知撰写更长的消息或减少合作时获得了更大的话语权。人们认为这些智能体比向单个 AI 系统提供意见更公平,恢复了直接参与时公平性差异的 82%。

If you build agent-based deliberation, cap message length and set shared behavior rules, or the most assertive prompts will tilt the outcome.

如果你构建基于智能体的审议机制,必须限制消息长度并设定共享的行为规则,否则最强势的提示词将会扭曲结果。

更进一步:量化金融体系

看懂新闻只是起点——沿量化金融路径,把它变成能交付的工程能力

进入量化体系 →

相似阅读

关联信息,但可能不是同一事件