Anthropic· @AnthropicAI · X·· 2026-04-16
AI 导读
我们共同撰写的关于潜意识学习——即 LLM 如何通过数据中的隐藏信号传递偏好或不对齐等特征——的研究今日发表于 @Nature。 阅读论文：https://www.nature.com/articles/s41586-026-10319-8 [引用 @OwainEvans_UK]：我们关于 Subliminal Learning 的论文刚刚在 Nature 发表！ 去年七月我们发布了预印本。研究表明 LLM 可以通过与该特征无关的数据（看似无意义的数字）传递特征（例如喜欢猫头鹰）。 有什么新内容？🧵 https://t.co/Iiv9sgjJki
正文 · 原文
Research we co-authored on subliminal learning—how LLMs can pass on traits like preferences or misalignment through hidden signals in data—was published today in @Nature.
Read the paper: https://www.nature.com/articles/s41586-026-10319-8
Our paper on Subliminal Learning was just published in Nature! Last July we released our preprint. It showed that LLMs can transmit traits (e.g. liking owls) through data that is unrelated to that trait (numbers that appear meaningless). What’s new?🧵 https://t.co/Iiv9sgjJki在 X 查看被引用的帖子
来源：Anthropic · x.com