# Zero-Shot Cross-Domain Dialogue State Tracking via Dual Low-Rank Adaptation

arXiv: https://arxiv.org/abs/2407.21633 · HTML: https://mlsanity.com/paper/2407.21633/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 50 references that are in the map.
- First posted on arXiv 31 Jul 2024.

## Builds on (most cited first, 4 of 4)

- [BERT-DST: Scalable End-to-End Dialogue State Tracking with Bidirectional Encoder Representations from Transformer](https://mlsanity.com/paper/1907.03040/) (2019)
- [An End-to-End Dialogue State Tracking System with Machine Reading Comprehension and Wide & Deep Classification](https://mlsanity.com/paper/1912.09297/) (2019)
- [A Dual Prompt Learning Framework for Few-Shot Dialogue State Tracking](https://mlsanity.com/paper/2201.05780/) (2022)
- [Parameter-Efficient Low-Resource Dialogue State Tracking by Prompt Tuning](https://mlsanity.com/paper/2301.10915/) (2023)

## Built on by (most cited first, 5 of 5)

- [Beyond Single-User Dialogue: Assessing Multi-User Dialogue State Tracking Capabilities of Large Language Models](https://mlsanity.com/paper/2506.10504/) (2025)
- [Schema Augmentation for Zero-Shot Domain Adaptation in Dialogue State Tracking](https://mlsanity.com/paper/2411.00150/) (2024)
- [EVL-MCoT: Enhanced Vision-Language Multi-CoT for Harmful Meme Detection](https://mlsanity.com/paper/2607.22016/) (2026)
- [Auto Review: Second Stage Error Detection for Highly Accurate Information Extraction from Phone Conversations](https://mlsanity.com/paper/2506.05400/) (2025)
- [HiCoLoRA: Addressing Context-Prompt Misalignment via Hierarchical Collaborative LoRA for Zero-Shot DST](https://mlsanity.com/paper/2509.19742/) (2025)

## Abstract (arXiv)

Zero-shot dialogue state tracking (DST) seeks to enable dialogue systems to transition to unfamiliar domains without manual annotation or extensive retraining. Prior research has approached this objective by embedding prompts into language models (LMs). Common methodologies include integrating prompts at the input layer or introducing learnable variables at each transformer layer. Nonetheless, each strategy exhibits inherent limitations. Prompts integrated at the input layer risk underutilization, with their impact potentially diminishing across successive transformer layers. Conversely, the addition of learnable variables to each layer can complicate the training process and increase inference latency. To tackle the issues mentioned above, this paper proposes Dual Low-Rank Adaptation (DualLoRA), a plug-and-play architecture designed for zero-shot DST. DualLoRA incorporates two distinct Low-Rank Adaptation (LoRA) components, targeting both dialogue context processing and prompt optimization, to ensure the comprehensive influence of prompts throughout the transformer model layers. This is achieved without incurring additional inference latency, showcasing an efficient integration into existing architectures. Through rigorous evaluation on the MultiWOZ and SGD datasets, DualLoRA demonstrates notable improvements across multiple domains, outperforming traditional baseline methods in zero-shot settings. Our code is accessible at: urlhttps://github.com/suntea233/DualLoRA.