用于大基础模型幻觉检测的李雅普诺夫探针
Lyapunov Probes for Hallucination Detection in Large Foundation Models
把 MLLM 的表征空间当作动力系统，用带导数稳定性约束的轻量探针在输入扰动下检测置信度是否单调衰减，从而区分事实稳定区与幻觉易发边界；这套扰动+稳定性探针可直接接到任意视觉语言模型的隐层特征上做幻觉判别。
原文依据 we propose Lyapunov Probes: lightweight networks trained with derivative-based stability constraints that enforce a monotonic decay in confidence under input perturbations
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论我们通过动力系统稳定性理论的视角来刻画大语言模型（LLM）与多模态大语言模型（MLLM）中的幻觉检测问题。我们不把幻觉当作一个简单的分类任务，而是将（多模态）大语言模型概念化为动力系统，其中事实性知识由表征空间内的稳定平衡点表示。我们的核心洞见是：幻觉往往出现在知识边界处，即分隔稳定区与不稳定区的过渡区域。为捕捉这一现象，我们提出李雅普诺夫探针：这是一类轻量网络，采用基于导数的稳定性约束进行训练，强制置信度在输入扰动下单调衰减。通过系统性的扰动分析并施加两阶段训练过程，这些探针能够可靠地区分稳定的事实区域与不稳定的、易发生幻觉的区域。在多种数据集与模型上的实验表明，该方法相较现有基线取得了一致性的提升。
英文原文摘要 1059 字符
We address hallucination detection in Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) by framing the problem through the lens of dynamical systems stability theory. Rather than treating hallucination as a straightforward classification task, we conceptualize (M)LLMs as dynamical systems, where factual knowledge is represented by stable equilibrium points within the representation space. Our main insight is that hallucinations tend to arise at the boundaries of knowledge--transition regions separating stable and unstable zones. To capture this phenomenon, we propose Lyapunov Probes: lightweight networks trained with derivative-based stability constraints that enforce a monotonic decay in confidence under input perturbations. By performing systematic perturbation analysis and applying a two-stage training process, these probes reliably distinguish between stable factual regions and unstable, hallucination-prone areas. Experiments on diverse datasets and models demonstrate consistent improvements over existing baselines.