LEMON transfers misbehavior monitoring across 16 LLMs zero-shot
LEMON lets teams monitor hallucinations and jailbreaks on new LLMs without repeatedly annotating data or paying for an external monitor. It reads each model’s attention maps token by token, using a graph neural network that stays stable when attention heads or layers differ between models. Across 16 LLMs and six datasets, it beat every baseline in zero-shot testing, by up to 14 ROC-AUC points.