---
title: "Structured Confidence–Guided Online Adaptation for LLM-based"
description: "Instead, the system builds up its own predictions as demonstrations. 43 references. Among them: 0."
authors: ["Pengyu Xu", "JingRen Hou", "Liping Jing", "Jian Yu"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.822/"
doi: "10.18653/v1/2026.findings-acl.822"
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/xu-2026-structured-confidence-guided-online-adaptation/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/xu-2026-structured-confidence-guided-online-adaptation/)

[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/51/) / Structured Confidence–Guided Online Adaptation for LLM-based Multi-Label Classification

# Structured Confidence–Guided Online Adaptation for LLM-based Multi-Label Classification

**Authors:** Pengyu Xu, JingRen Hou, Liping Jing and [Jian Yu](https://md.research.elamur.ai/free/en/authors/jian-yu/) · **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.822/) · [PDF](https://aclanthology.org/2026.findings-acl.822.pdf) · [DOI 10.18653/v1/2026.findings-acl.822](https://doi.org/10.18653/v1/2026.findings-acl.822) · [OpenAlex](https://openalex.org/W7166844693)

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

## Summary
LLM-based multi-label text classification through in-context learning usually treats every test input in isolation. This breaks down when data arrives as a stream whose distribution drifts and whose labels are long-tailed. The authors study online test-time adaptation that never updates model weights. Instead, the system builds up its own predictions as demonstrations. They identify two weaknesses. First, ordinary sequence or token likelihoods overstate certainty, because label names share prefixes and most tokens are almost deterministic. Second, simple caches filled by confidence or FIFO drift toward frequent, easy examples.

Their framework, SCOTTA, addresses both problems. It scores each label with L3R, which measures how strongly the model favours the label over valid rivals at the few positions where label paths branch. It then keeps a bounded exemplar memory using streaming submodular maximization, which trades off label coverage, semantic diversity and sample quality. On MOVIE, AAPD, RCV1 and StackExchange, SCOTTA improves Micro-F1 and Macro-F1 over LLM and non-LLM baselines, with the biggest gains on rare labels and very large label spaces. This makes training-free adaptation more practical for streaming classification.

## Key points
- **L3R (Label-set Local Likelihood Ratio):**
  - Competitors for a label at a decoding step are the labels with the same prefix.
  - At each step, a smoothed log-ratio compares the probability of the target token with the summed probability of competing tokens.
  - Steps are weighted by a softmax over binary entropy (controlled by α), so true branching points dominate the score.
- **Submodular Memory Bank (SMB):**
  - Reliable predictions enter a fixed-size cache, managed by streaming submodular optimization.
  - The objective balances coverage (weight λ1), diversity (λ2) and quality (λ3).
  - For each new input, relevant exemplars are retrieved from the cache and inserted into the prompt.
- **Evaluation:**
  - Four benchmarks: MOVIE, AAPD, RCV1, StackExchange (SE).
  - Reported metrics are Micro-F1 and Macro-F1.
- **Sensitivity analysis:**
  - Best retrieval size is k=4 on MOVIE (small label set) and k=8 on SE (extreme label space).
  - Results stay stable across a range of λ1 values.
- **Limitations:**
  - The method needs token log-probabilities, which some APIs do not expose.
  - Confidence scoring, retrieval and cache updates add inference cost.
  - It depends on embedding quality.
  - Confident errors may still accumulate under severe distribution shift.

*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

- [Beijing Jiaotong University](https://md.research.elamur.ai/free/en/universities/beijing-jiaotong-university/) — University, Beijing, China · 28 works · 1,754 citations

📚 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: Pengyu Xu, JingRen Hou, Liping Jing and Jian Yu. 2026. Structured Confidence–Guided Online Adaptation for LLM-based Multi-Label Classification. 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{xu2026structured,
  title = {{Structured Confidence–Guided Online Adaptation for LLM-based Multi-Label Classification}},
  author = {Pengyu Xu, JingRen Hou, Liping Jing and Jian Yu},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.822},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.822}
}
```

- [← previous Structure-Aware Zero-Shot Relational Learning for Knowledge Graphs without External Knowledge](https://md.research.elamur.ai/free/en/papers/xu-2026-structure-aware-zero-shot-relational/)
- [next → Structured Dialogue Refinement: Building Retrieval-Augmented Question Answering on Goal-Oriented Dialogues](https://md.research.elamur.ai/free/en/papers/wu-2026-structured-dialogue-refinement-building-retrieval/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/51/)

## References

43 references, 7 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. John Arevalo, Thamar Solorio, Manuel Montes y Gómez, and Fabio A. González. 2017. Gated multimodal units for information fusion. ArXiv, abs/1702.01992. — [arXiv:1702.01992](https://arxiv.org/abs/1702.01992) [find](https://scholar.google.com/scholar?q=John+Arevalo%2C+Thamar+Solorio%2C+Manuel+Montes+y+G%C3%B3mez%2C+and+Fabio+A%2E+Gonz%C3%A1lez%2E+2017%2E+Gated+multimodal+units+for+information+fusion%2E+ArXiv%2C+abs%2F1702%2E01992%2E+%E2%80%94+%5BarXiv%3A1702%2E01992%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F1702%2E)
2. Ashwinkumar Badanidiyuru, Baharan Mirzasoleiman, Amin Karbasi, and Andreas Krause. 2014. Streaming submodular maximization: massive data summarization on the fly. In Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’14, page 671–680, New York, N… [find](https://scholar.google.com/scholar?q=Ashwinkumar+Badanidiyuru%2C+Baharan+Mirzasoleiman%2C+Amin+Karbasi%2C+and+Andreas+Krause%2E+2014%2E+Streaming+submodular+maximization%3A+massive+data+summarization+on+the+fly%2E+In+Proceedings+of+the+20th+ACM+SIGKDD)
3. Fan Bai, Hamid Hassanzadeh, Ardavan Saeedi, and Mark Dredze. 2025. LLMs are better than you think: Label-guided in-context learning for named entity recognition. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 28372–28392, Suzhou, China. Association f… [find](https://scholar.google.com/scholar?q=Fan+Bai%2C+Hamid+Hassanzadeh%2C+Ardavan+Saeedi%2C+and+Mark+Dredze%2E+2025%2E+LLMs+are+better+than+you+think%3A+Label%2Dguided+in%2Dcontext+learning+for+named+entity+recognition%2E+In+Proceedings+of+the+2025+Conference+)
4. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, et al. 2020. [Language models are few-shot learners](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/). In Advances in Neural Information Processing Systems (NeurIPS).
5. Wei-Cheng Chang, Daniel L. Jiang, Hsiang-Fu Yu, Choon-Hui Teo, Jiong Zhang, Kai Zhong, Kedarnath Kolluri, Qie Hu, Nikhil Shandilya, Vyacheslav Ievgrafov, Japinder Singh, and Inderjit S. Dhillon. 2021. Extreme multi-label learning for semantic matching in product search. In KDD ’21: The 27th ACM SIGK… [find](https://scholar.google.com/scholar?q=Wei%2DCheng+Chang%2C+Daniel+L%2E+Jiang%2C+Hsiang%2DFu+Yu%2C+Choon%2DHui+Teo%2C+Jiong+Zhang%2C+Kai+Zhong%2C+Kedarnath+Kolluri%2C+Qie+Hu%2C+Nikhil+Shandilya%2C+Vyacheslav+Ievgrafov%2C+Japinder+Singh%2C+and+Inderjit+S%2E+Dhillon%2E+2021%2E)
6. Tianyu Gao, Xingcheng Yao, and Danqi Chen. 2021. [SimCSE: Simple contrastive learning of sentence embeddings](https://md.research.elamur.ai/free/en/papers/gao-2021-simcse-simple-contrastive-learning-sentence/). In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 6894–6910, Online and Punta Cana, Dominican Republic. Association for Computational Linguistic…
7. Baijun Ji, Xiangyu Duan, Zhenyu Qiu, Tong Zhang, Junhui Li, Hao Yang, and Min Zhang. 2024. Submodular-based in-context example selection for LLMs-based machine translation. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC… [find](https://scholar.google.com/scholar?q=Baijun+Ji%2C+Xiangyu+Duan%2C+Zhenyu+Qiu%2C+Tong+Zhang%2C+Junhui+Li%2C+Hao+Yang%2C+and+Min+Zhang%2E+2024%2E+Submodular%2Dbased+in%2Dcontext+example+selection+for+LLMs%2Dbased+machine+translation%2E+In+Proceedings+of+the+2024+)
8. Katrin Kirchhoff and Jeff Bilmes. 2014. Submodularity for data selection in statistical machine translation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). [find](https://scholar.google.com/scholar?q=Katrin+Kirchhoff+and+Jeff+Bilmes%2E+2014%2E+Submodularity+for+data+selection+in+statistical+machine+translation%2E+In+Proceedings+of+the+2014+Conference+on+Empirical+Methods+in+Natural+Language+Processing+%28)
9. Lorenz Kuhn, Yarin Gal, and Sebastian Farquhar. 2023. Semantic uncertainty in large language models. In International Conference on Learning Representations (ICLR). [find](https://scholar.google.com/scholar?q=Lorenz+Kuhn%2C+Yarin+Gal%2C+and+Sebastian+Farquhar%2E+2023%2E+Semantic+uncertainty+in+large+language+models%2E+In+International+Conference+on+Learning+Representations+%28ICLR%29%2E)
10. David D. Lewis, Yiming Yang, Tony G. Rose, and Fan Li. 2004. [Rcv1: A new benchmark collection for text categorization research](https://md.research.elamur.ai/free/en/papers/lewis-2004-rcv1-benchmark-collection-text-categorization/). Journal of Machine Learning Research, 5:361–397.
11. Ang Li, Yiquan Wu, Ming Cai, Adam Jatowt, Xiang Zhou, Weiming Lu, Changlong Sun, Fei Wu, and Kun Kuang. 2025a. Legal judgment prediction based on knowledge-enhanced multi-task and multi-label text classification. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Ass… [find](https://scholar.google.com/scholar?q=Ang+Li%2C+Yiquan+Wu%2C+Ming+Cai%2C+Adam+Jatowt%2C+Xiang+Zhou%2C+Weiming+Lu%2C+Changlong+Sun%2C+Fei+Wu%2C+and+Kun+Kuang%2E+2025a%2E+Legal+judgment+prediction+based+on+knowledge%2Denhanced+multi%2Dtask+and+multi%2Dlabel+text+cla)
12. Yue Li, Zhixue Zhao, and Carolina Scarton. 2025b. Label set optimization via activation distribution kurtosis for zero-shot classification with generative models. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 31724–31741, Suzhou, China. Association… [find](https://scholar.google.com/scholar?q=Yue+Li%2C+Zhixue+Zhao%2C+and+Carolina+Scarton%2E+2025b%2E+Label+set+optimization+via+activation+distribution+kurtosis+for+zero%2Dshot+classification+with+generative+models%2E+In+Proceedings+of+the+2025+Conference)
13. Stephanie Lin, Jacob Hilton, and Owain Evans. 2022. Teaching models to express their uncertainty in words. Preprint, arXiv:2205.14334. [find](https://scholar.google.com/scholar?q=Stephanie+Lin%2C+Jacob+Hilton%2C+and+Owain+Evans%2E+2022%2E+Teaching+models+to+express+their+uncertainty+in+words%2E+Preprint%2C+arXiv%3A2205%2E14334%2E)
14. Yuqi Lin, Minghao Chen, Kaipeng Zhang, Hengjia Li, Mingming Li, Zheng Yang, Dongqin Lv, Binbin Lin, Haifeng Liu, and Deng Cai. 2024. Tagclip: a local-to-global framework to enhance open-vocabulary multi-label classification of clip without training. In Proceedings of the Thirty-Eighth AAAI Conferenc… [find](https://scholar.google.com/scholar?q=Yuqi+Lin%2C+Minghao+Chen%2C+Kaipeng+Zhang%2C+Hengjia+Li%2C+Mingming+Li%2C+Zheng+Yang%2C+Dongqin+Lv%2C+Binbin+Lin%2C+Haifeng+Liu%2C+and+Deng+Cai%2E+2024%2E+Tagclip%3A+a+local%2Dto%2Dglobal+framework+to+enhance+open%2Dvocabulary+mul)
15. An Liu, Zonghan Yang, Zhenhe Zhang, Qingyuan Hu, Peng Li, Ming Yan, Ji Zhang, Fei Huang, and Yang Liu. 2024. PANDA: Preference adaptation for enhancing domain-specific abilities of LLMs. In Findings of the Association for Computational Linguistics: ACL 2024, pages 10960–10977, Bangkok, Thailand. Ass… [find](https://scholar.google.com/scholar?q=An+Liu%2C+Zonghan+Yang%2C+Zhenhe+Zhang%2C+Qingyuan+Hu%2C+Peng+Li%2C+Ming+Yan%2C+Ji+Zhang%2C+Fei+Huang%2C+and+Yang+Liu%2E+2024%2E+PANDA%3A+Preference+adaptation+for+enhancing+domain%2Dspecific+abilities+of+LLMs%2E+In+Findings+o)
16. Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. [Roberta: A robustly optimized bert pretraining approach](https://md.research.elamur.ai/free/en/papers/liu-2019-roberta-robustly-optimized-bert-pretraining/). arXiv preprint arXiv:1907.11692.
17. Jing Ma. 2024. Improved self-training for test-time adaptation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 23701–23710. [find](https://scholar.google.com/scholar?q=Jing+Ma%2E+2024%2E+Improved+self%2Dtraining+for+test%2Dtime+adaptation%2E+In+Proceedings+of+the+IEEE%2FCVF+Conference+on+Computer+Vision+and+Pattern+Recognition+%28CVPR%29%2C+pages+23701%E2%80%9323710%2E)
18. Marcus Ma, Georgios Chochlakis, Niyantha Maruthu Pandiyan, Jesse Thomason, and Shrikanth Narayanan. 2025. Large language models do multi-label classification differently. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 2472–2495, Suzhou, China. Associ… [find](https://scholar.google.com/scholar?q=Marcus+Ma%2C+Georgios+Chochlakis%2C+Niyantha+Maruthu+Pandiyan%2C+Jesse+Thomason%2C+and+Shrikanth+Narayanan%2E+2025%2E+Large+language+models+do+multi%2Dlabel+classification+differently%2E+In+Proceedings+of+the+2025+Co)
19. Qianwen Ma, Chunyuan Yuan, Wei Zhou, and Songlin Hu. 2021. Label-specific dual graph neural network for multi-label text classification. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processi… [find](https://scholar.google.com/scholar?q=Qianwen+Ma%2C+Chunyuan+Yuan%2C+Wei+Zhou%2C+and+Songlin+Hu%2E+2021%2E+Label%2Dspecific+dual+graph+neural+network+for+multi%2Dlabel+text+classification%2E+In+Proceedings+of+the+59th+Annual+Meeting+of+the+Association+fo)
20. Andrey Malinin and Mark Gales. 2021. Uncertainty estimation in autoregressive structured prediction. In International Conference on Learning Representations (ICLR). [find](https://scholar.google.com/scholar?q=Andrey+Malinin+and+Mark+Gales%2E+2021%2E+Uncertainty+estimation+in+autoregressive+structured+prediction%2E+In+International+Conference+on+Learning+Representations+%28ICLR%29%2E)
21. OpenAI. 2024a. Gpt-3.5 turbo model documentation. [https://platform.openai.com/docs/](https://platform.openai.com/docs/) models/gpt-3.5-turbo. Accessed: 2026-01-06. [↗](https://platform.openai.com/docs/)
22. OpenAI. 2024b. Hello gpt-4o. [https://openai.com/](https://openai.com/) index/hello-gpt-4o/. Accessed: 2026-01-06. [↗](https://openai.com/)
23. Diego Ortego, Marlon Rodríguez, Mario Almagro, Kunal Dahiya, David Jiménez, and Juan C. SanMiguel. 2025. Large language models meet extreme multi-label classification: Scaling and multi-modal framework. Preprint, arXiv:2511.13189. — [arXiv:2511.13189](https://arxiv.org/abs/2511.13189) [find](https://scholar.google.com/scholar?q=Diego+Ortego%2C+Marlon+Rodr%C3%ADguez%2C+Mario+Almagro%2C+Kunal+Dahiya%2C+David+Jim%C3%A9nez%2C+and+Juan+C%2E+SanMiguel%2E+2025%2E+Large+language+models+meet+extreme+multi%2Dlabel+classification%3A+Scaling+and+multi%2Dmodal+framewor)
24. Pramit Saha, Divyanshu Mishra, Felix Wagner, Konstantinos Kamnitsas, and J. Alison Noble. 2025. Incongruent multimodal federated learning for medical vision and language-based multi-label disease detection. In AAAI-25, Sponsored by the Association for the Advancement of Artificial Intelligence, Febr… [find](https://scholar.google.com/scholar?q=Pramit+Saha%2C+Divyanshu+Mishra%2C+Felix+Wagner%2C+Konstantinos+Kamnitsas%2C+and+J%2E+Alison+Noble%2E+2025%2E+Incongruent+multimodal+federated+learning+for+medical+vision+and+language%2Dbased+multi%2Dlabel+disease+dete)
25. Souvika Sarkar, Dongji Feng, and Shubhra Kanti Karmaker Santu. 2023. Zero-shot multi-label topic inference with sentence encoders and llms. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023, Singapore, December 6-10, 2023, pages 16218–16233. Associ… [find](https://scholar.google.com/scholar?q=Souvika+Sarkar%2C+Dongji+Feng%2C+and+Shubhra+Kanti+Karmaker+Santu%2E+2023%2E+Zero%2Dshot+multi%2Dlabel+topic+inference+with+sentence+encoders+and+llms%2E+In+Proceedings+of+the+2023+Conference+on+Empirical+Methods+i)
26. Kaitao Song, Xu Tan, Tao Qin, Jianfeng Lu, and Tie-Yan Liu. 2020. [Mpnet: Masked and permuted pre-training for language understanding](https://md.research.elamur.ai/free/en/papers/song-2020-mpnet-masked-permuted-pre-training/). arXiv preprint arXiv:2004.09297.
27. Yi Su, Yunpeng Tai, Yixin Ji, Juntao Li, Yan Bowen, and Min Zhang. 2024. Demonstration augmentation for zero-shot in-context learning. In Findings of the Association for Computational Linguistics: ACL 2024, pages 14232–14244, Bangkok, Thailand. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Yi+Su%2C+Yunpeng+Tai%2C+Yixin+Ji%2C+Juntao+Li%2C+Yan+Bowen%2C+and+Min+Zhang%2E+2024%2E+Demonstration+augmentation+for+zero%2Dshot+in%2Dcontext+learning%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+ACL)
28. Shijie Tang, Yuan Yao, Suwei Zhang, Feng Xu, Tianxiao Gu, Hanghang Tong, Xiaohui Yan, and Jian Lu. 2019. An integral tag recommendation model for textual content. In Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence and Thirty-First Innovative Applications of Artificial Inte… [find](https://scholar.google.com/scholar?q=Shijie+Tang%2C+Yuan+Yao%2C+Suwei+Zhang%2C+Feng+Xu%2C+Tianxiao+Gu%2C+Hanghang+Tong%2C+Xiaohui+Yan%2C+and+Jian+Lu%2E+2019%2E+An+integral+tag+recommendation+model+for+textual+content%2E+In+Proceedings+of+the+Thirty%2DThird+AA)
29. Yau-Shian Wang, Ta-Chung Chi, Ruohong Zhang, and Yiming Yang. 2023. PESCO: prompt-enhanced self contrastive learning for zero-shot text classification. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2023, Toronto, Canada, July… [find](https://scholar.google.com/scholar?q=Yau%2DShian+Wang%2C+Ta%2DChung+Chi%2C+Ruohong+Zhang%2C+and+Yiming+Yang%2E+2023%2E+PESCO%3A+prompt%2Denhanced+self+contrastive+learning+for+zero%2Dshot+text+classification%2E+In+Proceedings+of+the+61st+Annual+Meeting+of+the)
30. Mingxuan Xia, Zhijie Jiang, Haobo Wang, Junbo Zhao, Tianlei Hu, and Gang Chen. 2025. Ensembling prompting strategies for zero-shot hierarchical text classification with large language models. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 18189– 1820… [find](https://scholar.google.com/scholar?q=Mingxuan+Xia%2C+Zhijie+Jiang%2C+Haobo+Wang%2C+Junbo+Zhao%2C+Tianlei+Hu%2C+and+Gang+Chen%2E+2025%2E+Ensembling+prompting+strategies+for+zero%2Dshot+hierarchical+text+classification+with+large+language+models%2E+In+Proce)
31. Xin Xia, David Lo, Xinyu Wang, and Bo Zhou. 2013. Tag recommendation in software information sites. In Proceedings of the 10th Working Conference on Mining Software Repositories (MSR), pages 287–296. IEEE. [find](https://scholar.google.com/scholar?q=Xin+Xia%2C+David+Lo%2C+Xinyu+Wang%2C+and+Bo+Zhou%2E+2013%2E+Tag+recommendation+in+software+information+sites%2E+In+Proceedings+of+the+10th+Working+Conference+on+Mining+Software+Repositories+%28MSR%29%2C+pages+287%E2%80%93296%2E+)
32. An Yang et al. 2024. Qwen2.5 technical report. arXiv preprint arXiv:2412.15115. [find](https://scholar.google.com/scholar?q=An+Yang+et+al%2E+2024%2E+Qwen2%2E5+technical+report%2E+arXiv+preprint+arXiv%3A2412%2E15115%2E)
33. An Yang et al. 2025. [Qwen3 technical report](https://md.research.elamur.ai/free/en/papers/yang-2025-qwen3-technical-report/). arXiv preprint arXiv:2505.09388.
34. Pengcheng Yang, Xu Sun, Wei Li, Shuming Ma, Wei Wu, and Houfeng Wang. 2018. [Sgm: sequence generation model for multi-label classification](https://md.research.elamur.ai/free/en/papers/yang-2018-sgm-sequence-generation-model-multi/). arXiv preprint arXiv:1806.04822.
35. Ronghui You, Zihan Zhang, Ziye Wang, Suyang Dai, Hiroshi Mamitsuka, and Shanfeng Zhu. 2019. Attentionxml: Label tree-based attention-aware deep model for high-performance extreme multi-label text classification. Advances in Neural Information Processing Systems, 32:5820–5830. [find](https://scholar.google.com/scholar?q=Ronghui+You%2C+Zihan+Zhang%2C+Ziye+Wang%2C+Suyang+Dai%2C+Hiroshi+Mamitsuka%2C+and+Shanfeng+Zhu%2E+2019%2E+Attentionxml%3A+Label+tree%2Dbased+attention%2Daware+deep+model+for+high%2Dperformance+extreme+multi%2Dlabel+text+clas)
36. Jinbin Zhang, Nasib Ullah, and Rohit Babbar. 2025. Large language model as a teacher for zero-shot tagging at extreme scales. In Proceedings of the 31st International Conference on Computational Linguistics, pages 3465–3478, Abu Dhabi, UAE. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Jinbin+Zhang%2C+Nasib+Ullah%2C+and+Rohit+Babbar%2E+2025%2E+Large+language+model+as+a+teacher+for+zero%2Dshot+tagging+at+extreme+scales%2E+In+Proceedings+of+the+31st+International+Conference+on+Computational+Lingu)
37. Qian-Wen Zhang, Ximing Zhang, Zhao Yan, Ruifang Liu, Yunbo Cao, and Min-Ling Zhang. 2021. Correlation-guided representation for multi-label text classification. In IJCAI, pages 3363–3369. [find](https://scholar.google.com/scholar?q=Qian%2DWen+Zhang%2C+Ximing+Zhang%2C+Zhao+Yan%2C+Ruifang+Liu%2C+Yunbo+Cao%2C+and+Min%2DLing+Zhang%2E+2021%2E+Correlation%2Dguided+representation+for+multi%2Dlabel+text+classification%2E+In+IJCAI%2C+pages+3363%E2%80%933369%2E)
38. Dequan Wang, Evan Shelhamer, Shaoteng Liu, Bruno Olshausen, and Trevor Darrell. 2021. Tent: Fully test-time adaptation by entropy minimization. In International Conference on Learning Representations (ICLR). [find](https://scholar.google.com/scholar?q=Dequan+Wang%2C+Evan+Shelhamer%2C+Shaoteng+Liu%2C+Bruno+Olshausen%2C+and+Trevor+Darrell%2E+2021%2E+Tent%3A+Fully+test%2Dtime+adaptation+by+entropy+minimization%2E+In+International+Conference+on+Learning+Representations+)
39. Renrui Zhang, Zhang Wei, Rongyao Fang, Peng Gao, Kunchang Li, Jifeng Dai, Yu Jiao Qiao, and Hongsheng Li. 2022. Tip-adapter: Training-free adaption of clip for few-shot classification. volume abs/2207.09519. — [arXiv:2207.09519](https://arxiv.org/abs/2207.09519) [find](https://scholar.google.com/scholar?q=Renrui+Zhang%2C+Zhang+Wei%2C+Rongyao+Fang%2C+Peng+Gao%2C+Kunchang+Li%2C+Jifeng+Dai%2C+Yu+Jiao+Qiao%2C+and+Hongsheng+Li%2E+2022%2E+Tip%2Dadapter%3A+Training%2Dfree+adaption+of+clip+for+few%2Dshot+classification%2E+volume+abs%2F2207)
40. Y. Wang et al. 2025. Streaming stochastic submodular maximization with on-demand user requests. In Advances in Neural Information Processing Systems (NeurIPS). [find](https://scholar.google.com/scholar?q=Y%2E+Wang+et+al%2E+2025%2E+Streaming+stochastic+submodular+maximization+with+on%2Ddemand+user+requests%2E+In+Advances+in+Neural+Information+Processing+Systems+%28NeurIPS%29%2E)
41. Yunyi Zhang, Minhao Jiang, Yu Meng, Yu Zhang, and Jiawei Han. 2023. Pieclass: Weakly-supervised text classification with prompting and noise-robust iterative ensemble training. In Proceedings of the 2023 [find](https://scholar.google.com/scholar?q=Yunyi+Zhang%2C+Minhao+Jiang%2C+Yu+Meng%2C+Yu+Zhang%2C+and+Jiawei+Han%2E+2023%2E+Pieclass%3A+Weakly%2Dsupervised+text+classification+with+prompting+and+noise%2Drobust+iterative+ensemble+training%2E+In+Proceedings+of+the+2)
42. Conference on Empirical Methods in Natural Language Processing, EMNLP 2023, Singapore, December 6-10, 2023, pages 12655–12670. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Conference+on+Empirical+Methods+in+Natural+Language+Processing%2C+EMNLP+2023%2C+Singapore%2C+December+6%2D10%2C+2023%2C+pages+12655%E2%80%9312670%2E+Association+for+Computational+Linguistics%2E)
43. Yaxin Zhu and Hamed Zamani. 2024. ICXML: an in-context learning framework for zero-shot extreme multi-label classification. In Findings of the Association for Computational Linguistics: NAACL 2024, Mexico City, Mexico, June 16-21, 2024, pages 2086– 2098. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Yaxin+Zhu+and+Hamed+Zamani%2E+2024%2E+ICXML%3A+an+in%2Dcontext+learning+framework+for+zero%2Dshot+extreme+multi%2Dlabel+classification%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+NAACL+2024%2C+Me)

*Updated 2 November 2026*