Token-level hallucination detectors are evaluated as classifiers, by AUC over all tokens, yet a streaming monitor is judged by its reaction time: the number of tokens that pass between the onset of a hallucination and the alarm. We formulate hallucination onset detection as a quickest change detection problem. A first-order Markov model of the latent faithful/hallucinated state, validated on RAGTruth, places the task inside classical change-point theory and yields Lorden's lower bound on detection delay: about 1.3 tokens at a false-alarm rate of 0.01. We then show that a causal recurrent labeler acts as a CUSUM with a learned increment. Among the onsets it catches it detects in 11-13 tokens, against 31 for a linear per-token baseline, though at this false-alarm budget every detector catches under a third of onsets and the recall-honest delay is 56-66 tokens: low-false-alarm onset detection is hard. A controlled decomposition attributes the speed advantage mostly to a better per-token score rather than to temporal accumulation. An information-rate optimality theorem of Donsker-Varadhan type explains the remaining order-of-magnitude gap: the learned score realizes only 1/4.5 of the divergence the features carry, a deficit that recalibration cannot remove, with the remainder a finite-horizon effect. Classification metrics conceal this delay structure; sequential analysis makes it measurable.

翻译：基于令牌级幻觉检测器通常通过所有令牌上的AUC作为分类器进行评估，然而流式监控器则以其反应时间——即从幻觉发生到警报触发之间通过的令牌数量——作为评判标准。我们将幻觉起始检测形式化为一个最快变化检测问题。一个基于RAGTruth验证的潜在忠实/幻觉状态的一阶马尔可夫模型，将任务置于经典变点理论框架内，并得出洛登关于检测延迟的下界：在虚警率为0.01时约为1.3个令牌。随后我们证明，因果循环标注器相当于一个具有学习增量的CUSUM。在能捕获的幻觉起始中，该模型在11-13个令牌内检测到，而线性逐令牌基线需要31个令牌，尽管在此虚警预算下，每个检测器仅能捕获不到三分之一的起始，且考虑召回率的诚实延迟为56-66个令牌：低虚警率下的起始检测任务具有挑战性。通过受控分解，该速度优势主要归因于更好的逐令牌得分而非时间累积。唐斯克-瓦拉丹型信息率最优定理解释了其余的数量级差距：学习得分仅实现了特征所携带散度的1/4.5，这一缺陷无法通过重新校准消除，剩余部分为有限时间效应。分类指标掩盖了这种延迟结构；而序列分析使其变得可量化。