mlsanityData to 14 Oct 2026

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

arXiv 2509.19742 ↗First posted 24 Sep 2025cs.CL cs.AI cs.IRcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 42 of its 62 references that are in the map. First posted on arXiv 24 Sep 2025.

Builds on

42 of 62 references.

References · 42

  1. 2019Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Datasetcited by 434
  2. 2018Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfacescited by 377
  3. 2020A Simple Language Model for Task-Oriented Dialoguecited by 332
  4. 2024PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Modelscited by 269
  5. 2019Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systemscited by 216
  6. 2025Hierarchical Reasoning Modelcited by 177
  7. 2024LoRA-GA: Low-Rank Adaptation with Gradient Approximationcited by 141
  8. 2021Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue Systemcited by 139
  9. 2024HydraLoRA: An Asymmetric LoRA Architecture for Efficient Fine-Tuningcited by 123
  10. 2019SUMBT: Slot-Utterance Matching for Universal and Scalable Belief Trackingcited by 63
  11. 2021Leveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue State Trackingcited by 61
  12. 2024Efficient Deformable ConvNets: Rethinking Dynamic and Sparse Operator for Vision Applicationscited by 50
30 more
  1. 2024RoSA: Accurate Parameter-Efficient Fine-Tuning via Robust Adaptationcited by 48
  2. 2025Parameter-Efficient Fine-Tuning for Foundation Modelscited by 45
  3. 2024Fantastic Semantics and Where to Find Them: Investigating Which Layers of Generative LLMs Reflect Lexical Semanticscited by 44
  4. 2020A Sequence-to-Sequence Approach to Dialogue State Trackingcited by 43
  5. 2023ChatGPT for Zero-shot Dialogue State Tracking: A Solution or an Opportunity?cited by 38
  6. 2023Can Whisper perform speech-based in-context learning?cited by 35
  7. 2024Large Language Models as Zero-shot Dialogue State Tracker through Function Callingcited by 34
  8. 2021Zero-shot Generalization in Dialog State Tracking through Generative Question Answeringcited by 33
  9. 2024HiVG: Hierarchical Multimodal Fine-grained Modulation for Visual Groundingcited by 31
  10. 2025HSplitLoRA: A Heterogeneous Split Parameter-Efficient Fine-Tuning Framework for Large Language Modelscited by 31
  11. 2020MA-DST: Multi-Attention Based Scalable Dialog State Trackingcited by 24
  12. 2024Enhancing Dialogue State Tracking Models through LLM-backed User-Agents Simulationcited by 24
  13. 2023Fairness-Aware Structured Pruning in Transformerscited by 22
  14. 2024Spectral Adapter: Fine-Tuning in Spectral Spacecited by 21
  15. 2019Scaling Multi-Domain Dialogue State Tracking via Query Reformulationcited by 20
  16. 2024MiLoRA: Efficient Mixture of Low-Rank Adaptation for Large Language Models Fine-tuningcited by 19
  17. 2024MTL-LoRA: Low-Rank Adaptation for Multi-Task Learningcited by 17
  18. 2024Simulation-Free Hierarchical Latent Policy Planning for Proactive Dialoguescited by 14
  19. 2024Instruct Once, Chat Consistently in Multiple Rounds: An Efficient Tuning Framework for Dialoguecited by 11
  20. 2023Divide, Conquer, and Combine: Mixture of Semantic-Independent Experts for Zero-Shot Dialogue State Trackingcited by 10
  21. 2023Prompter: Zero-shot Adaptive Prefixes for Dialogue State Tracking Domain Adaptationcited by 7
  22. 2024Diverse and Effective Synthetic Data Generation for Adaptable Zero-Shot Dialogue State Trackingcited by 6
  23. 2025Olica: Efficient Structured Pruning of Large Language Models without Retrainingcited by 6
  24. 2024Zero-Shot Cross-Domain Dialogue State Tracking via Dual Low-Rank Adaptationcited by 5
  25. 2024Adaptive Parameter-Efficient Federated Fine-Tuning on Heterogeneous Devicescited by 5
  26. 2018Selective Feature Connection Mechanism: Concatenating Multi-layer CNN Features with a Feature Selectorcited by 4
  27. 2024Fine-tuning with HED-IT: The impact of human post-editing for dialogical language modelscited by 3
  28. 2025Beyond Single-User Dialogue: Assessing Multi-User Dialogue State Tracking Capabilities of Large Language Modelscited by 2
  29. 2024MoPE: Mixture of Prefix Experts for Zero-Shot Dialogue State Trackingcited by 1
  30. 2024Intent-driven In-context Learning for Few-shot Dialogue State Trackingcited by 1

Built on by

Not cited yet.