牛哥精选 · 本月

📋 全部 🤖 AI·大模型 ⚡ 效率工具 📝 深度技术 🚀 产品观察 💰 商业科技 🔓 开源项目 🎨 设计创意 📖 阅读推荐 🏷 资源合集 🌱 成长效率

🤖 AI·大模型 arXiv NLP 2026-06-02

The Invisible Coalition Partner: How LLMs Vote When Democracy Gets Concrete

LLM在抽象问卷中左倾，但在具体政策投票中却未必，双工具方法颠覆认知。

arXiv:2606.00048v1 Announce Type: cross Abstract: Prior research has established that instruction-tuned large language models exhibit left-of-center p…

llm 政治偏见投票行为具体政策实验设计

📝 深度技术 arXiv AI 2026-05-25

It's the humans, not the data: Geopolitical bias in LLMs originates in post-training, amplified by the language of the prompt

研究发现大模型地缘政治偏见来自后训练而非数据，提示语言会放大偏见，颠覆传统认知。

arXiv:2605.23825v1 Announce Type: cross Abstract: It has generally been assumed that geopolitical bias in language models originates from the training…

大语言模型地缘政治偏见后训练提示工程人工智能对齐

📅 日期

2026-05-20 2026-05-19

🐂 牛哥精选

The Invisible Coalition Partner: How LLMs Vote When Democracy Gets Concrete

It's the humans, not the data: Geopolitical bias in LLMs originates in post-training, amplified by the language of the prompt

📅 日期