cs.AI, cs.CL, cs.LG

Hallucination as Trajectory Commitment: Causal Evidence for Asymmetric Attractor Dynamics in Transformer Generation

arXiv:2604.15400v1 Announce Type: cross
Abstract: We present causal evidence that hallucination in autoregressive language models is an early trajectory commitment governed by asymmetric attractor dynamics. Using same-prompt bifurcation, in which we r…