---
title: "HiCoLoRA — paper by Zhang et al. (2026) — summary and ideas"
description: "This mismatch shows up in three ways: uniform treatment of transformer layers, entanglement of domain-shared and… 51 references."
authors: ["Shuyu Zhang", "Yifan Wei", "Xinru Wang", "Yanmin Zhu", "Yangfan He", "Yixuan Weng", "Yujie Liu", "Bin Li"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.1876/"
doi: "10.18653/v1/2026.findings-acl.1876"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/zhang-2026-hicolora-addressing-context-prompt-misalignment/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/zhang-2026-hicolora-addressing-context-prompt-misalignment/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/36/) / HiCoLoRA: Addressing Context-Prompt Misalignment via Hierarchical Collaborative LoRA for Zero-Shot DST

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

**Authors:** [Shuyu Zhang](https://md.research.elamur.ai/free/en/authors/shuyu-zhang/), [Yifan Wei](https://md.research.elamur.ai/free/en/authors/yifan-wei/), [Xinru Wang](https://md.research.elamur.ai/free/en/authors/xinru-wang/), [Yanmin Zhu](https://md.research.elamur.ai/free/en/authors/yanmin-zhu/), Yangfan He, [Yixuan Weng](https://md.research.elamur.ai/free/en/authors/yixuan-weng/), [Yujie Liu](https://md.research.elamur.ai/free/en/authors/yujie-liu/) and [Bin Li](https://md.research.elamur.ai/free/en/authors/bin-li/) · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: ACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.findings-acl.1876/) · [PDF](https://aclanthology.org/2026.findings-acl.1876.pdf) · [DOI 10.18653/v1/2026.findings-acl.1876](https://doi.org/10.18653/v1/2026.findings-acl.1876) · [OpenAlex](https://openalex.org/W7166802871)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
The paper addresses zero-shot dialog state tracking (zs-DST), in which a task-oriented dialog system must fill slots for domains it never saw during training. The authors identify the main obstacle as a mismatch between evolving dialog context and fixed slot prompts. This mismatch shows up in three ways: uniform treatment of transformer layers, entanglement of domain-shared and domain-specific signals, and erosion of pre-trained knowledge when LoRA starts from random weights.

Their framework, HiCoLoRA, has three parts:
- **Hierarchical LoRA:** lower layers use heuristic grouping of adapters, and higher layers allow full interaction among them.
- **Spectral Joint Domain-Slot Clustering:** this finds transferable slot associations and steers an adaptive gate that blends a domain-agnostic branch (UniRep-LoRA) with a domain-specific one (SemAdapt-LoRA).
- **SemSVD-Init:** adapters are initialised from principal singular directions weighted by domain-slot relevance, rather than from noise.

On MultiWOZ and SGD, using strict seen/unseen domain splits, HiCoLoRA reports state-of-the-art joint goal accuracy. Because adapters can be merged at inference, its runtime cost stays close to that of plain LoRA, which makes it relevant for practical low-annotation dialog systems.

## Key points
- Compared with the previous SOTA (DualLoRA), HiCoLoRA raises average JGA by 5.4% on MultiWOZ and by 9.4% on SGD.
- In ablations, removing spectral clustering costs 7.4% JGA, and SemSVD-Init gives 7.1% higher JGA than random initialization.
- The zero-shot protocol trains only on seen domains; for example, the Police and Hospital domains are excluded in MultiWOZ 2.1.
- At inference, the SemAdapt-LoRA matrices are merged into a single pair (A_total, B_total), so latency stays near standard LoRA levels.
- Code is released at github.com/carsonz/HiCoLoRA. Reported weaknesses include ambiguous slot boundaries, rare slot values, and highly domain-exclusive slots.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Shanghai Jiao Tong University](https://md.research.elamur.ai/free/en/universities/shanghai-jiao-tong-university/) — University, Shanghai, China · 212 works · 19,544 citations
- [Chinese Academy of Sciences](https://md.research.elamur.ai/free/en/government/chinese-academy-of-sciences/) — Government body, Beijing, China · 246 works · 24,951 citations
- [The University of Sydney](https://md.research.elamur.ai/free/en/universities/the-university-of-sydney/) — University, Sydney, Australia · 49 works · 68,350 citations
- [Beihang University](https://md.research.elamur.ai/free/en/universities/beihang-university/) — University, Beijing, China · 86 works · 9,097 citations
- [Westlake University](https://md.research.elamur.ai/free/en/universities/westlake-university/) — University, Hangzhou, China · 51 works · 8,572 citations
- [University of Minnesota](https://md.research.elamur.ai/free/en/universities/university-of-minnesota/) — University, Minneapolis, United States · 28 works · 2,021 citations
- [Beijing Institute of Graphic Communication](https://md.research.elamur.ai/free/en/universities/beijing-institute-of-graphic-communication/) — University, Beijing, China · 3 works

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works

## Cite

Cite as: Shuyu Zhang, Yifan Wei, Xinru Wang, Yanmin Zhu, Yangfan He, Yixuan Weng, Yujie Liu and Bin Li. 2026. HiCoLoRA: Addressing Context-Prompt Misalignment via Hierarchical Collaborative LoRA for Zero-Shot DST. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{zhang2026hicolora,
  title = {{HiCoLoRA: Addressing Context-Prompt Misalignment via Hierarchical Collaborative LoRA for Zero-Shot DST}},
  author = {Shuyu Zhang, Yifan Wei, Xinru Wang, Yanmin Zhu, Yangfan He, Yixuan Weng, Yujie Liu and Bin Li},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.1876},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.1876}
}
```

- [← previous Heterogeneity in Formal Linguistic Competence of Language Models: Is Data the Real Bottleneck?](https://md.research.elamur.ai/free/en/papers/renduchintala-2026-heterogeneity-formal-linguistic-competence-language/)
- [next → Hidden Sentiments: The Impact of Low-level Adversarial Perturbations on Arabic Sentiment Analysis Services](https://md.research.elamur.ai/free/en/papers/abdelkader-2026-hidden-sentiments-impact-low-level/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/36/)

## References

51 references, 6 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Taha Aksu, Min-Yen Kan, and Nancy Chen. 2023. Prompter: Zero-shot adaptive prefixes for dialogue state tracking domain adaptation. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4588–4603, Toronto, Canada. Association for Com… [find](https://scholar.google.com/scholar?q=Taha+Aksu%2C+Min%2DYen+Kan%2C+and+Nancy+Chen%2E+2023%2E+Prompter%3A+Zero%2Dshot+adaptive+prefixes+for+dialogue+state+tracking+domain+adaptation%2E+In+Proceedings+of+the+61st+Annual+Meeting+of+the+Association+for+Comp)
2. Alice Coucke, Alaa Saade, Adrien Ball, Théodore Bluche, Alexandre Caulier, David Leroy, Clément Doumouro, Thibault Gisselbrecht, Francesco Caltagirone, Thibaut Lavril, Maël Primet, and Joseph Dureau. 2018. [Snips voice platform: an embedded spoken language understanding system for private-by-design v…](https://md.research.elamur.ai/free/en/papers/coucke-2018-snips-voice-platform-embedded-spoken/)
3. Xiaoyu Dong, Yujie Feng, Zexin Lu, Guangyuan Shi, and Xiao-Ming Wu. 2024. Zero-shot cross-domain dialogue state tracking via context-aware auto-prompting and instruction-following contrastive decoding. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 8… [find](https://scholar.google.com/scholar?q=Xiaoyu+Dong%2C+Yujie+Feng%2C+Zexin+Lu%2C+Guangyuan+Shi%2C+and+Xiao%2DMing+Wu%2E+2024%2E+Zero%2Dshot+cross%2Ddomain+dialogue+state+tracking+via+context%2Daware+auto%2Dprompting+and+instruction%2Dfollowing+contrastive+decoding)
4. Mihail Eric, Rahul Goel, Shachi Paul, Abhishek Sethi, Sanchit Agarwal, Shuyang Gao, Adarsh Kumar, Anuj Goyal, Peter Ku, and Dilek Hakkani-Tur. 2020. MultiWOZ 2.1: A consolidated multi-domain dialogue dataset with state corrections and state tracking baselines. In Proceedings of the Twelfth Language… [find](https://scholar.google.com/scholar?q=Mihail+Eric%2C+Rahul+Goel%2C+Shachi+Paul%2C+Abhishek+Sethi%2C+Sanchit+Agarwal%2C+Shuyang+Gao%2C+Adarsh+Kumar%2C+Anuj+Goyal%2C+Peter+Ku%2C+and+Dilek+Hakkani%2DTur%2E+2020%2E+MultiWOZ+2%2E1%3A+A+consolidated+multi%2Ddomain+dialogue+)
5. Yue Feng, Yang Wang, and Hang Li. 2021. A Sequence-to-Sequence Approach to Dialogue State Tracking. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 171… [find](https://scholar.google.com/scholar?q=Yue+Feng%2C+Yang+Wang%2C+and+Hang+Li%2E+2021%2E+A+Sequence%2Dto%2DSequence+Approach+to+Dialogue+State+Tracking%2E+In+Proceedings+of+the+59th+Annual+Meeting+of+the+Association+for+Computational+Linguistics+and+the+1)
6. Yujie Feng, Zexin Lu, Bo Liu, Liming Zhan, and Xiao-Ming Wu. 2023. Towards LLM-driven dialogue state tracking. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 739–755, Singapore. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Yujie+Feng%2C+Zexin+Lu%2C+Bo+Liu%2C+Liming+Zhan%2C+and+Xiao%2DMing+Wu%2E+2023%2E+Towards+LLM%2Ddriven+dialogue+state+tracking%2E+In+Proceedings+of+the+2023+Conference+on+Empirical+Methods+in+Natural+Language+Processing)
7. James D. Finch and Jinho D. Choi. 2024. Diverse and effective synthetic data generation for adaptable zero-shot dialogue state tracking. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 12527–12544, Miami, Florida, USA. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=James+D%2E+Finch+and+Jinho+D%2E+Choi%2E+2024%2E+Diverse+and+effective+synthetic+data+generation+for+adaptable+zero%2Dshot+dialogue+state+tracking%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+E)
8. Zhihan Guo, Yifei Zhang, Zhuo Zhang, Zenglin Xu, and Irwin King. 2024. Fedhlt: Efficient federated low-rank adaption with hierarchical language tree for multilingual modeling. In Companion Proceedings of the ACM Web Conference 2024, WWW ’24, page 1558–1567, New York, NY, USA. Association for Computi… [find](https://scholar.google.com/scholar?q=Zhihan+Guo%2C+Yifei+Zhang%2C+Zhuo+Zhang%2C+Zenglin+Xu%2C+and+Irwin+King%2E+2024%2E+Fedhlt%3A+Efficient+federated+low%2Drank+adaption+with+hierarchical+language+tree+for+multilingual+modeling%2E+In+Companion+Proceedings)
9. Jiujun He and Huazhen Lin. 2025. Olica: Efficient structured pruning of large language models without retraining. In Forty-second International Conference on Machine Learning. [find](https://scholar.google.com/scholar?q=Jiujun+He+and+Huazhen+Lin%2E+2025%2E+Olica%3A+Efficient+structured+pruning+of+large+language+models+without+retraining%2E+In+Forty%2Dsecond+International+Conference+on+Machine+Learning%2E)
10. Tao He, Lizi Liao, Yixin Cao, Yuanxing Liu, Yiheng Sun, Zerui Chen, Ming Liu, and Bing Qin. 2025. Simulation-free hierarchical latent policy planning for proactive dialogues. Proceedings of the AAAI Conference on Artificial Intelligence, 39(22):24032– 24040. [find](https://scholar.google.com/scholar?q=Tao+He%2C+Lizi+Liao%2C+Yixin+Cao%2C+Yuanxing+Liu%2C+Yiheng+Sun%2C+Zerui+Chen%2C+Ming+Liu%2C+and+Bing+Qin%2E+2025%2E+Simulation%2Dfree+hierarchical+latent+policy+planning+for+proactive+dialogues%2E+Proceedings+of+the+AAAI+C)
11. Michael Heck, Nurul Lubis, Benjamin Ruppik, Renato Vukovic, Shutong Feng, Christian Geishauser, Hsien-chin Lin, Carel van Niekerk, and Milica Gasic. 2023. ChatGPT for zero-shot dialogue state tracking: A solution or an opportunity? In Proceedings of the 61st Annual Meeting of the Association for Com… [find](https://scholar.google.com/scholar?q=Michael+Heck%2C+Nurul+Lubis%2C+Benjamin+Ruppik%2C+Renato+Vukovic%2C+Shutong+Feng%2C+Christian+Geishauser%2C+Hsien%2Dchin+Lin%2C+Carel+van+Niekerk%2C+and+Milica+Gasic%2E+2023%2E+ChatGPT+for+zero%2Dshot+dialogue+state+tracking)
12. Charles T. Hemphill, John J. Godfrey, and George R. Doddington. 1990. The ATIS spoken language systems pilot corpus. In Speech and Natural Language: Proceedings of a Workshop Held at Hidden Valley, Pennsylvania, June 24-27,1990. [find](https://scholar.google.com/scholar?q=Charles+T%2E+Hemphill%2C+John+J%2E+Godfrey%2C+and+George+R%2E+Doddington%2E+1990%2E+The+ATIS+spoken+language+systems+pilot+corpus%2E+In+Speech+and+Natural+Language%3A+Proceedings+of+a+Workshop+Held+at+Hidden+Valley%2C+Pe)
13. Ehsan Hosseini-Asl, Bryan McCann, Chien-Sheng Wu, Semih Yavuz, and Richard Socher. 2020. [A simple language model for task-oriented dialogue](https://md.research.elamur.ai/free/en/papers/hosseini-asl-2020-simple-language-model-task-oriented/). In Proceedings of the 34th International Conference on Neural Information Processing Systems, NIPS ’20, Red Hook, NY, USA. Curran Associates Inc.
14. Faramarz Jabbarvaziri and Lutz Lampe. 2025. Parameter-efficient online fine-tuning of ml-based hybrid beamforming with lora. IEEE Wireless Communications Letters, 14(5):1451–1455. [find](https://scholar.google.com/scholar?q=Faramarz+Jabbarvaziri+and+Lutz+Lampe%2E+2025%2E+Parameter%2Defficient+online+fine%2Dtuning+of+ml%2Dbased+hybrid+beamforming+with+lora%2E+IEEE+Wireless+Communications+Letters%2C+14%285%29%3A1451%E2%80%931455%2E)
15. Adarsh Kumar, Peter Ku, Anuj Goyal, Angeliki Metallinou, and Dilek Hakkani-Tur. 2020. Ma-dst: Multi-attention-based scalable dialog state tracking. Proceedings of the AAAI Conference on Artificial Intelligence, 34:8107–8114. [find](https://scholar.google.com/scholar?q=Adarsh+Kumar%2C+Peter+Ku%2C+Anuj+Goyal%2C+Angeliki+Metallinou%2C+and+Dilek+Hakkani%2DTur%2E+2020%2E+Ma%2Ddst%3A+Multi%2Dattention%2Dbased+scalable+dialog+state+tracking%2E+Proceedings+of+the+AAAI+Conference+on+Artificial+Int)
16. Hwaran Lee, Jinsik Lee, and Tae-Yoon Kim. 2019. [SUMBT: Slot-utterance matching for universal and scalable belief tracking](https://md.research.elamur.ai/free/en/papers/lee-2019-sumbt-slot-utterance-matching-universal/). In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5478–5483, Florence, Italy. Association for Computational Linguistics.
17. Shuyang Li, Jin Cao, Mukund Sridhar, Henghui Zhu, Shang-Wen Li, Wael Hamza, and Julian McAuley. 2021a. Zero-shot generalization in dialog state tracking through generative question answering. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguisti… [find](https://scholar.google.com/scholar?q=Shuyang+Li%2C+Jin+Cao%2C+Mukund+Sridhar%2C+Henghui+Zhu%2C+Shang%2DWen+Li%2C+Wael+Hamza%2C+and+Julian+McAuley%2E+2021a%2E+Zero%2Dshot+generalization+in+dialog+state+tracking+through+generative+question+answering%2E+In+Proce)
18. Shuyang Li, Jin Cao, Mukund Sridhar, Henghui Zhu, Shang-Wen Li, Wael Hamza, and Julian McAuley. 2021b. Zero-shot Generalization in Dialog State Tracking through Generative Question Answering. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguisti… [find](https://scholar.google.com/scholar?q=Shuyang+Li%2C+Jin+Cao%2C+Mukund+Sridhar%2C+Henghui+Zhu%2C+Shang%2DWen+Li%2C+Wael+Hamza%2C+and+Julian+McAuley%2E+2021b%2E+Zero%2Dshot+Generalization+in+Dialog+State+Tracking+through+Generative+Question+Answering%2E+In+Proce)
19. Zekun Li, Zhiyu Chen, Mike Ross, Patrick Huber, Seungwhan Moon, Zhaojiang Lin, Xin Dong, Adithya Sagar, Xifeng Yan, and Paul Crook. 2024. Large language models as zero-shot dialogue state tracker through function calling. In Proceedings of the 62nd Annual Meeting of the Association for Computational… [find](https://scholar.google.com/scholar?q=Zekun+Li%2C+Zhiyu+Chen%2C+Mike+Ross%2C+Patrick+Huber%2C+Seungwhan+Moon%2C+Zhaojiang+Lin%2C+Xin+Dong%2C+Adithya+Sagar%2C+Xifeng+Yan%2C+and+Paul+Crook%2E+2024%2E+Large+language+models+as+zero%2Dshot+dialogue+state+tracker+thro)
20. Zhaojiang Lin, Bing Liu, Seungwhan Moon, Paul Crook, Zhenpeng Zhou, Zhiguang Wang, Zhou Yu, Andrea Madotto, Eunjoon Cho, and Rajen Subba. 2021. Leveraging slot descriptions for zero-shot cross-domain dialogue StateTracking. In Proceedings of the 2021 Conference of the North American Chapter of the A… [find](https://scholar.google.com/scholar?q=Zhaojiang+Lin%2C+Bing+Liu%2C+Seungwhan+Moon%2C+Paul+Crook%2C+Zhenpeng+Zhou%2C+Zhiguang+Wang%2C+Zhou+Yu%2C+Andrea+Madotto%2C+Eunjoon+Cho%2C+and+Rajen+Subba%2E+2021%2E+Leveraging+slot+descriptions+for+zero%2Dshot+cross%2Ddomain+)
21. Zheng Lin, Yuxin Zhang, Zhe Chen, Zihan Fang, Xianhao Chen, Praneeth Vepakomma, Wei Ni, Jun Luo, and Yue Gao. 2025. Hsplitlora: A heterogeneous split parameter-efficient fine-tuning framework for large language models. Preprint, arXiv:2505.02795. — [arXiv:2505.02795](https://arxiv.org/abs/2505.02795) [find](https://scholar.google.com/scholar?q=Zheng+Lin%2C+Yuxin+Zhang%2C+Zhe+Chen%2C+Zihan+Fang%2C+Xianhao+Chen%2C+Praneeth+Vepakomma%2C+Wei+Ni%2C+Jun+Luo%2C+and+Yue+Gao%2E+2025%2E+Hsplitlora%3A+A+heterogeneous+split+parameter%2Defficient+fine%2Dtuning+framework+for+larg)
22. Jun Liu, Yunming Liao, Hongli Xu, Yang Xu, Jianchun Liu, and Chen Qian. 2025a. Adaptive parameter-efficient federated fine-tuning on heterogeneous devices. IEEE Transactions on Mobile Computing, 24(11):12533–12549. [find](https://scholar.google.com/scholar?q=Jun+Liu%2C+Yunming+Liao%2C+Hongli+Xu%2C+Yang+Xu%2C+Jianchun+Liu%2C+and+Chen+Qian%2E+2025a%2E+Adaptive+parameter%2Defficient+federated+fine%2Dtuning+on+heterogeneous+devices%2E+IEEE+Transactions+on+Mobile+Computing%2C+24%2811)
23. Zeming Liu, Haifeng Wang, Zeyang Lei, Zheng-Yu Niu, Hua Wu, and Wanxiang Che. 2025b. Towards few-shot mixed-type dialogue generation. Science China Information Sciences, 68(2):122105. [find](https://scholar.google.com/scholar?q=Zeming+Liu%2C+Haifeng+Wang%2C+Zeyang+Lei%2C+Zheng%2DYu+Niu%2C+Hua+Wu%2C+and+Wanxiang+Che%2E+2025b%2E+Towards+few%2Dshot+mixed%2Dtype+dialogue+generation%2E+Science+China+Information+Sciences%2C+68%282%29%3A122105%2E)
24. Zhu Liu, Cunliang Kong, Ying Liu, and Maosong Sun. 2024. Fantastic semantics and where to find them: Investigating which layers of generative LLMs reflect lexical semantics. In Findings of the Association for Computational Linguistics: ACL 2024, pages 14551–14558, Bangkok, Thailand. Association for… [find](https://scholar.google.com/scholar?q=Zhu+Liu%2C+Cunliang+Kong%2C+Ying+Liu%2C+and+Maosong+Sun%2E+2024%2E+Fantastic+semantics+and+where+to+find+them%3A+Investigating+which+layers+of+generative+LLMs+reflect+lexical+semantics%2E+In+Findings+of+the+Associa)
25. Xiang Luo, Zhiwen Tang, Jin Wang, and Xuejie Zhang. 2024. Zero-shot cross-domain dialogue state tracking via dual low-rank adaptation. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5746–5765, Bangkok, Thailand. Association f… [find](https://scholar.google.com/scholar?q=Xiang+Luo%2C+Zhiwen+Tang%2C+Jin+Wang%2C+and+Xuejie+Zhang%2E+2024%2E+Zero%2Dshot+cross%2Ddomain+dialogue+state+tracking+via+dual+low%2Drank+adaptation%2E+In+Proceedings+of+the+62nd+Annual+Meeting+of+the+Association+for+)
26. Fanxu Meng, Zhaohui Wang, and Muhan Zhang. 2024. [Pissa: Principal singular values and singular vectors adaptation of large language models](https://md.research.elamur.ai/free/en/papers/meng-2024-pissa-principal-singular-values-singular/). In Advances in Neural Information Processing Systems, volume 37, pages 121038–121072. Curran Associates, Inc.
27. Mahdi Nikdan, Soroush Tabesh, Elvir Crnčević, and Dan Alistarh. 2024. RoSA: Accurate parameter-efficient fine-tuning via robust adaptation. In Proceedings of the 41st International Conference on Machine Learning, volume 235 of Proceedings of Machine Learning Research, pages 38187–38206. PMLR. [find](https://scholar.google.com/scholar?q=Mahdi+Nikdan%2C+Soroush+Tabesh%2C+Elvir+Crnc%CC%8Cevic%CC%81%2C+and+Dan+Alistarh%2E+2024%2E+RoSA%3A+Accurate+parameter%2Defficient+fine%2Dtuning+via+robust+adaptation%2E+In+Proceedings+of+the+41st+International+Conference+on+Mac)
28. Daniela Occhipinti, Michele Marchi, Irene Mondella, Huiyuan Lai, Felice Dell’Orletta, Malvina Nissim, and Marco Guerini. 2024. Fine-tuning with HED-IT: The impact of human post-editing for dialogical language models. In Findings of the Association for Computational Linguistics: ACL 2024, pages 11892… [find](https://scholar.google.com/scholar?q=Daniela+Occhipinti%2C+Michele+Marchi%2C+Irene+Mondella%2C+Huiyuan+Lai%2C+Felice+Dell%E2%80%99Orletta%2C+Malvina+Nissim%2C+and+Marco+Guerini%2E+2024%2E+Fine%2Dtuning+with+HED%2DIT%3A+The+impact+of+human+post%2Dediting+for+dialogical+)
29. Abhinav Rastogi, Xiaoxue Zang, Srinivas Sunkara, Raghav Gupta, and Pranav Khaitan. 2020. [Towards scalable multi-domain conversational agents: The schema-guided dialogue dataset](https://md.research.elamur.ai/free/en/papers/rastogi-2019-towards-scalable-multi-domain-conversational/). Proceedings of the AAAI Conference on Artificial Intelligence, 34(05):8689–8696.
30. Pushpendre Rastogi, Arpit Gupta, Tongfei Chen, and Mathias Lambert. 2019. Scaling multi-domain dialogue state tracking via query reformulation. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2… [find](https://scholar.google.com/scholar?q=Pushpendre+Rastogi%2C+Arpit+Gupta%2C+Tongfei+Chen%2C+and+Mathias+Lambert%2E+2019%2E+Scaling+multi%2Ddomain+dialogue+state+tracking+via+query+reformulation%2E+In+Proceedings+of+the+2019+Conference+of+the+North+Ameri)
31. Sangmin Song, Juhwan Choi, JungMin Yun, and Young-Bin Kim. 2025. Beyond single-user dialogue: Assessing multi-user dialogue state tracking capabilities of large language models. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 20018–20029, Suzhou, China. Association fo… [find](https://scholar.google.com/scholar?q=Sangmin+Song%2C+Juhwan+Choi%2C+JungMin+Yun%2C+and+Young%2DBin+Kim%2E+2025%2E+Beyond+single%2Duser+dialogue%3A+Assessing+multi%2Duser+dialogue+state+tracking+capabilities+of+large+language+models%2E+In+Findings+of+the+Ass)
32. Yixuan Su, Lei Shu, Elman Mansimov, Arshit Gupta, Deng Cai, Yi-An Lai, and Yi Zhang. 2022. Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4661–4676, Dub… [find](https://scholar.google.com/scholar?q=Yixuan+Su%2C+Lei+Shu%2C+Elman+Mansimov%2C+Arshit+Gupta%2C+Deng+Cai%2C+Yi%2DAn+Lai%2C+and+Yi+Zhang%2E+2022%2E+Multi%2DTask+Pre%2DTraining+for+Plug%2Dand%2DPlay+Task%2DOriented+Dialogue+System%2E+In+Proceedings+of+the+60th+Annual+Me)
33. Tianwen Tang, Tong Zhu, Haodong Liu, Yin Bai, Jia Cheng, and Wenliang Chen. 2024. MoPE: Mixture of prefix experts for zero-shot dialogue state tracking. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages… [find](https://scholar.google.com/scholar?q=Tianwen+Tang%2C+Tong+Zhu%2C+Haodong+Liu%2C+Yin+Bai%2C+Jia+Cheng%2C+and+Wenliang+Chen%2E+2024%2E+MoPE%3A+Mixture+of+prefix+experts+for+zero%2Dshot+dialogue+state+tracking%2E+In+Proceedings+of+the+2024+Joint+International+)
34. Chunlin Tian, Zhan Shi, Zhijiang Guo, Li Li, and Chengzhong Xu. 2024. Hydralora: An asymmetric lora architecture for efficient fine-tuning. In Advances in Neural Information Processing Systems, volume 37, pages 9565–9584. Curran Associates, Inc. [find](https://scholar.google.com/scholar?q=Chunlin+Tian%2C+Zhan+Shi%2C+Zhijiang+Guo%2C+Li+Li%2C+and+Chengzhong+Xu%2E+2024%2E+Hydralora%3A+An+asymmetric+lora+architecture+for+efficient+fine%2Dtuning%2E+In+Advances+in+Neural+Information+Processing+Systems%2C+volume)
35. Guan Wang, Jin Li, Yuhao Sun, Xing Chen, Changling Liu, Yue Wu, Meng Lu, Sen Song, and Yasin Abbasi Yadkori. 2025. Hierarchical reasoning model. Preprint, arXiv:2506.21734. [find](https://scholar.google.com/scholar?q=Guan+Wang%2C+Jin+Li%2C+Yuhao+Sun%2C+Xing+Chen%2C+Changling+Liu%2C+Yue+Wu%2C+Meng+Lu%2C+Sen+Song%2C+and+Yasin+Abbasi+Yadkori%2E+2025%2E+Hierarchical+reasoning+model%2E+Preprint%2C+arXiv%3A2506%2E21734%2E)
36. Jian Wang, Chak Tou Leong, Jiashuo Wang, Dongding Lin, Wenjie Li, and Xiaoyong Wei. 2024a. Instruct once, chat consistently in multiple rounds: An efficient tuning framework for dialogue. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Paper… [find](https://scholar.google.com/scholar?q=Jian+Wang%2C+Chak+Tou+Leong%2C+Jiashuo+Wang%2C+Dongding+Lin%2C+Wenjie+Li%2C+and+Xiaoyong+Wei%2E+2024a%2E+Instruct+once%2C+chat+consistently+in+multiple+rounds%3A+An+efficient+tuning+framework+for+dialogue%2E+In+Proceedin)
37. Qingyue Wang, Yanan Cao, Piji Li, Yanhe Fu, Zheng Lin, and Li Guo. 2022. Slot dependency modeling for zero-shot cross-domain dialogue state tracking. In Proceedings of the 29th International Conference on Computational Linguistics, pages 510–520, Gyeongju, Republic of Korea. International Committee… [find](https://scholar.google.com/scholar?q=Qingyue+Wang%2C+Yanan+Cao%2C+Piji+Li%2C+Yanhe+Fu%2C+Zheng+Lin%2C+and+Li+Guo%2E+2022%2E+Slot+dependency+modeling+for+zero%2Dshot+cross%2Ddomain+dialogue+state+tracking%2E+In+Proceedings+of+the+29th+International+Conferenc)
38. Qingyue Wang, Liang Ding, Yanan Cao, Yibing Zhan, Zheng Lin, Shi Wang, Dacheng Tao, and Li Guo. 2023. Divide, Conquer, and Combine: Mixture of Semantic-Independent Experts for Zero-Shot Dialogue State Tracking. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistic… [find](https://scholar.google.com/scholar?q=Qingyue+Wang%2C+Liang+Ding%2C+Yanan+Cao%2C+Yibing+Zhan%2C+Zheng+Lin%2C+Shi+Wang%2C+Dacheng+Tao%2C+and+Li+Guo%2E+2023%2E+Divide%2C+Conquer%2C+and+Combine%3A+Mixture+of+Semantic%2DIndependent+Experts+for+Zero%2DShot+Dialogue+State)
39. Shaowen Wang, Linxi Yu, and Jian Li. 2024b. Lora-ga: Low-rank adaptation with gradient approximation. In Advances in Neural Information Processing Systems, volume 37, pages 54905–54931. Curran Associates, Inc. [find](https://scholar.google.com/scholar?q=Shaowen+Wang%2C+Linxi+Yu%2C+and+Jian+Li%2E+2024b%2E+Lora%2Dga%3A+Low%2Drank+adaptation+with+gradient+approximation%2E+In+Advances+in+Neural+Information+Processing+Systems%2C+volume+37%2C+pages+54905%E2%80%9354931%2E+Curran+Associa)
40. Siyin Wang, Chao-Han Yang, Ji Wu, and Chao Zhang. 2024c. Can whisper perform speech-based in-context learning? In ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 13421–13425. [find](https://scholar.google.com/scholar?q=Siyin+Wang%2C+Chao%2DHan+Yang%2C+Ji+Wu%2C+and+Chao+Zhang%2E+2024c%2E+Can+whisper+perform+speech%2Dbased+in%2Dcontext+learning%3F+In+ICASSP+2024+%2D+2024+IEEE+International+Conference+on+Acoustics%2C+Speech+and+Signal+Proce)
41. Chien-Sheng Wu, Andrea Madotto, Ehsan Hosseini-Asl, Caiming Xiong, Richard Socher, and Pascale Fung. 2019. [Transferable multi-domain state generator for task-oriented dialogue systems](https://md.research.elamur.ai/free/en/papers/wu-2019-transferable-multi-domain-state-generator/). In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 808–819, Florence…
42. Yuwen Xiong, Zhiqi Li, Yuntao Chen, Feng Wang, Xizhou Zhu, Jiapeng Luo, Wenhai Wang, Tong Lu, Hongsheng Li, Yu Qiao, Lewei Lu, Jie Zhou, and Jifeng Dai. 2024. Efficient deformable convnets: Rethinking dynamic and sparse operator for vision applications. In 2024 IEEE/CVF Conference on Computer Vision… [find](https://scholar.google.com/scholar?q=Yuwen+Xiong%2C+Zhiqi+Li%2C+Yuntao+Chen%2C+Feng+Wang%2C+Xizhou+Zhu%2C+Jiapeng+Luo%2C+Wenhai+Wang%2C+Tong+Lu%2C+Hongsheng+Li%2C+Yu+Qiao%2C+Lewei+Lu%2C+Jie+Zhou%2C+and+Jifeng+Dai%2E+2024%2E+Efficient+deformable+convnets%3A+Rethinking)
43. Yaming Yang, Dilxat Muhtar, Yelong Shen, Yuefeng Zhan, Jianfeng Liu, Yujing Wang, Hao Sun, Weiwei Deng, Feng Sun, Qi Zhang, Weizhu Chen, and Yunhai Tong. 2025. Mtl-lora: Low-rank adaptation for multi-task learning. Proceedings of the AAAI Conference on Artificial Intelligence, 39(20):22010–22018. [find](https://scholar.google.com/scholar?q=Yaming+Yang%2C+Dilxat+Muhtar%2C+Yelong+Shen%2C+Yuefeng+Zhan%2C+Jianfeng+Liu%2C+Yujing+Wang%2C+Hao+Sun%2C+Weiwei+Deng%2C+Feng+Sun%2C+Qi+Zhang%2C+Weizhu+Chen%2C+and+Yunhai+Tong%2E+2025%2E+Mtl%2Dlora%3A+Low%2Drank+adaptation+for+multi%2D)
44. Zihao Yi, Zhe Xu, and Ying Shen. 2025. Intent-driven in-context learning for few-shot dialogue state tracking. In ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 1–5. [find](https://scholar.google.com/scholar?q=Zihao+Yi%2C+Zhe+Xu%2C+and+Ying+Shen%2E+2025%2E+Intent%2Ddriven+in%2Dcontext+learning+for+few%2Dshot+dialogue+state+tracking%2E+In+ICASSP+2025+%2D+2025+IEEE+International+Conference+on+Acoustics%2C+Speech+and+Signal+Proce)
45. Abdelrahman Zayed, Gonçalo Mordido, Samira Shabanian, Ioana Baldini, and Sarath Chandar. 2024. Fairness-aware structured pruning in transformers. Proceedings of the AAAI Conference on Artificial Intelligence, 38(20):22484–22492. [find](https://scholar.google.com/scholar?q=Abdelrahman+Zayed%2C+Gon%C3%A7alo+Mordido%2C+Samira+Shabanian%2C+Ioana+Baldini%2C+and+Sarath+Chandar%2E+2024%2E+Fairness%2Daware+structured+pruning+in+transformers%2E+Proceedings+of+the+AAAI+Conference+on+Artificial+Intel)
46. Dan Zhang, Tao Feng, Lilong Xue, Yuandong Wang, Yuxiao Dong, and Jie Tang. 2025. Parameter-efficient fine-tuning for foundation models. Preprint, arXiv:2501.13787. — [arXiv:2501.13787](https://arxiv.org/abs/2501.13787) [find](https://scholar.google.com/scholar?q=Dan+Zhang%2C+Tao+Feng%2C+Lilong+Xue%2C+Yuandong+Wang%2C+Yuxiao+Dong%2C+and+Jie+Tang%2E+2025%2E+Parameter%2Defficient+fine%2Dtuning+for+foundation+models%2E+Preprint%2C+arXiv%3A2501%2E13787%2E+%E2%80%94+%5BarXiv%3A2501%2E13787%5D%28https%3A%2F%2Farxiv%2Eo)
47. Dev Test Attraction Hotel Restaurant Taxi Train 2717 3381 3813 1654 3103 401 416 438 207 484 416 394 207 195 494 Total *Table 2: The dataset statistic of MultiWOZ.* Xingguang Wang, Xuxin Cheng, Juntong Song, Tong Zhang, and Cheng Niu. 2024d. Enhancing dialogue state tracking models through LLM-backe… [find](https://scholar.google.com/scholar?q=Dev+Test+Attraction+Hotel+Restaurant+Taxi+Train+2717+3381+3813+1654+3103+401+416+438+207+484+416+394+207+195+494+Total+%2ATable+2%3A+The+dataset+statistic+of+MultiWOZ%2E%2A+Xingguang+Wang%2C+Xuxin+Cheng%2C+Junton)
48. Linhui Xiao, Xiaoshan Yang, Fang Peng, Yaowei Wang, and Changsheng Xu. 2024. Hivg: Hierarchical multimodal fine-grained modulation for visual grounding. In Proceedings of the 32nd ACM International Conference on Multimedia, MM ’24, page 5460–5469, New York, NY, USA. Association for Computing Machine… [find](https://scholar.google.com/scholar?q=Linhui+Xiao%2C+Xiaoshan+Yang%2C+Fang+Peng%2C+Yaowei+Wang%2C+and+Changsheng+Xu%2E+2024%2E+Hivg%3A+Hierarchical+multimodal+fine%2Dgrained+modulation+for+visual+grounding%2E+In+Proceedings+of+the+32nd+ACM+International+Co)
49. Domain Domain Train Dev Test Buses Events Flights Media Messaging Music Payment Trains 2,280 3,509 2,747 1,113 NA 1,290 NA NA 329 418 391 179 NA 196 NA NA 526 592 506 364 298 347 222 350 Total 10,939 1,513 3,205 *Table 3: The dataset statistic of SGD.* Fangzhao Zhang and Mert Pilanci. 2025. Spectral… [find](https://scholar.google.com/scholar?q=Domain+Domain+Train+Dev+Test+Buses+Events+Flights+Media+Messaging+Music+Payment+Trains+2%2C280+3%2C509+2%2C747+1%2C113+NA+1%2C290+NA+NA+329+418+391+179+NA+196+NA+NA+526+592+506+364+298+347+222+350+Total+10%2C939+)
50. Jingfan Zhang, Yi Zhao, Dan Chen, Xing Tian, Huanran Zheng, and Wei Zhu. 2024. MiLoRA: Efficient mixture of low-rank adaptation for large language models fine-tuning. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 17071–17084, Miami, Florida, USA. Association for Com… [find](https://scholar.google.com/scholar?q=Jingfan+Zhang%2C+Yi+Zhao%2C+Dan+Chen%2C+Xing+Tian%2C+Huanran+Zheng%2C+and+Wei+Zhu%2E+2024%2E+MiLoRA%3A+Efficient+mixture+of+low%2Drank+adaptation+for+large+language+models+fine%2Dtuning%2E+In+Findings+of+the+Association+fo)
51. Yiyun Zhou, Chang Yao, and Jingyuan Chen. 2025. CoLA: Collaborative low-rank adaptation. In Findings of the Association for Computational Linguistics: ACL 2025, pages 14115–14130, Vienna, Austria. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Yiyun+Zhou%2C+Chang+Yao%2C+and+Jingyuan+Chen%2E+2025%2E+CoLA%3A+Collaborative+low%2Drank+adaptation%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+ACL+2025%2C+pages+14115%E2%80%9314130%2C+Vienna%2C+Austria%2E+Ass)

*Updated 2 November 2026*