AI RESEARCH
You Didn't Have to Say It like That: Subliminal Learning from Faithful Paraphrases
arXiv CS.LG
•
ArXi:2603.09517v1 Announce Type: cross When language models are trained on synthetic data, they (student model) can covertly acquire behavioral traits from the data-generating model (teacher model). Subliminal learning refers to the transmission of traits from a teacher to a student model via