Preconditioned Test-Time Adaptation for Out-of-Distribution Debiasing in Narrative Generation

ArXi:2603.13683v1 Announce Type: cross Although debiased LLMs perform well on known bias patterns, they often fail to generalize to unfamiliar bias prompts, producing toxic outputs. We first validate that such high-bias prompts constitute a \emph{distribution shift} via OOD detection, and show static models degrade under this shift.