Get started
Work

HiCoLoRA: Addressing Context-Prompt Misalignment via Hierarchical Collaborative LoRA for Zero-Shot DST

Year: 2025
Type: preprint
Abstract: 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.
Authors: Zhang, Shuyu, Wei, Yifan, Wang, Xinru, Zhu, Yanmin, He, Yangfan, Weng, Yixuan, Li, Bin, Liu, Yujie
Institutions: Shanghai Jiao Tong University, Beihang University, The University of Sydney, University of Minnesota, Westlake University, Chinese Academy of Sciences, Beijing Institute of Graphic Communication
Language: English
Open Access status: green
OpenAlex ID: W7083511737
Cites:
Cited by:
Related to: