Zero-shot Dialog State Tracking (zs-DST) is essential for enabling Task-Oriented Dialog Systems (TODs) to generalize to new domains without costly data annotation. A central challenge lies in the semantic misalignment between dynamic dialog contexts and static prompts, leading to inflexible cross-layer coordination, domain interference, and catastrophic forgetting. To tackle this, we propose Hierarchical Collaborative Low-Rank Adaptation (HiCoLoRA), a framework that enhances zero-shot slot inference through robust prompt alignment. It features a hierarchical LoRA architecture for dynamic layer-specific processing (combining lower-layer heuristic grouping and higher-layer full interaction), integrates Spectral Joint Domain-Slot Clustering to identify transferable associations (feeding an Adaptive Linear Fusion Mechanism), and employs Semantic-Enhanced SVD Initialization (SemSVD-Init) to preserve pre-trained knowledge. Experiments on multi-domain datasets MultiWOZ and SGD show that HiCoLoRA outperforms baselines, achieving SOTA in zs-DST. Code is available at https://github.com/carsonz/HiCoLoRA.

翻译：零样本对话状态追踪（zs-DST）对于使任务导向对话系统（TODs）能够泛化到新领域而无需昂贵的数据标注至关重要。其核心挑战在于动态对话上下文与静态提示之间的语义错位，这导致了不灵活的跨层协调、领域干扰以及灾难性遗忘。为解决这一问题，我们提出了分层协作低秩自适应（HiCoLoRA），这是一个通过鲁棒的提示对齐来增强零样本槽位推断的框架。该框架采用分层LoRA架构进行动态的层特异性处理（结合了低层的启发式分组和高层的完全交互），集成了谱联合领域-槽位聚类以识别可迁移的关联（馈入自适应线性融合机制），并采用语义增强的SVD初始化（SemSVD-Init）来保留预训练知识。在多领域数据集MultiWOZ和SGD上的实验表明，HiCoLoRA优于基线方法，在zs-DST任务上达到了最先进的性能。代码可在 https://github.com/carsonz/HiCoLoRA 获取。