Nathan Hu(@NathanHu12):New paper! In subliminal learning, LLMs transmit traits (e.g. loving cats) though seemingly unrelated data (e.g. numbers). We proactively detect these effects as readable prompts. To do so, we use the surprising ability of models to verbalize learned soft prompts.🧵

Nathan Hu

@NathanHu12

PhD @stanfordnlp | aspiring LLM biologist |

参加 September 2021

367 フォロー中 401 ファン

Nathan Hu@NathanHu12

2026.09.17 17:03

New paper! In subliminal learning, LLMs transmit traits (e.g. loving cats) though seemingly unrelated data (e.g. numbers). We proactively detect these effects as readable prompts. To do so, we use the surprising ability of models to verbalize learned soft prompts.🧵