Lying Is Just a Phase: The Hidden Alignment Transition in Language Model Scaling 事件

Lying Is Just a Phase: The Hidden Alignment Transition in Language Model Scaling arXiv:2605.18838v2 Announce Type: replace-cross Abstract: Scaling laws predict loss from compute but not how capabilities interact. We measure the coupling between reasoning and truthfulness across 63 base models from 16 families and find a regime change invisible to loss curves: below a family-dependent critical scale $N_c$, capabilities anticorrelate; above it, they cooperate. $N_c \approx 3.5$B parameters [2.9B,