---
title: "Incomplete In-context Learning — paper by Wang et al. (2026)"
description: "It studies cases where some classes have no labeled examples, for instance… 89.2% accuracy. 100 references, cited by 2 papers here."
authors: ["Wenqiang Wang", "Wen Yujia", "Yan Xiao", "Zhifeng Chen", "Yangshijie Zhang", "Peng Chen", "Mingbo Yang", "Xiaochun Cao"]
year: 2026
venue: "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2026.acl-long.1931/"
doi: "10.18653/v1/2026.acl-long.1931"
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/wang-2026-incomplete-context-learning/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/wang-2026-incomplete-context-learning/)

[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/7/) / Incomplete In-context Learning

# Incomplete In-context Learning

**Authors:** [Wenqiang Wang](https://md.research.elamur.ai/free/en/authors/wenqiang-wang/), Wen Yujia, [Yan Xiao](https://md.research.elamur.ai/free/en/authors/yan-xiao/), [Zhifeng Chen](https://md.research.elamur.ai/free/en/authors/zhifeng-chen/), [Yangshijie Zhang](https://md.research.elamur.ai/free/en/authors/yangshijie-zhang/), [Peng Chen](https://md.research.elamur.ai/free/en/authors/peng-chen/), Mingbo Yang and [Xiaochun Cao](https://md.research.elamur.ai/free/en/authors/xiaochun-cao/) · **Year:** 2026 · **Venue:** [Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/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.acl-long.1931/) · [PDF](https://aclanthology.org/2026.acl-long.1931.pdf) · [DOI 10.18653/v1/2026.acl-long.1931](https://doi.org/10.18653/v1/2026.acl-long.1931) · [OpenAlex](https://openalex.org/W4417515792)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · [2](https://md.research.elamur.ai/free/en/papers/wang-2026-incomplete-context-learning/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Standard in-context learning assumes that the retrieval pool has demonstrations for every output label. This paper drops that assumption. It studies cases where some classes have no labeled examples, for instance because the database is outdated, classes are highly imbalanced, or annotation follows a Positive-Unlabeled setup. The authors call this setting Incomplete In-context Learning (IICL). A pilot study with InternVL 2.5-8B on CIFAR-10 shows that accuracy drops as more labels go missing, even when only one is removed, although it stays above zero-shot prompting.

Their solution, IJIP (Iterative Judgments and Integrated Prediction), first turns one m-way decision into m yes/no questions. This way, even classes absent from the pool get usable "not this class" examples. A second step handles cases with zero or several positive answers by running a further ICL query over the candidate labels. A training-based variant groups labels into coarser semantic clusters and learns how many clusters to use for each input, which shortens prompts. Extensions cover regression, generation, semi-supervised data and images.

IJIP reaches state-of-the-art results and also helps when the label set is complete, so it matters wherever annotation lags behind the label space.

## Key points
- Evaluation covers six LLMs, seven tasks and eight datasets, including CIFAR-10, SNLI, SST5 and STS-B. Peak accuracy is 98.6% (InternVL 26B, CIFAR-10) and the best MSE is 0.62.
- With only one label present in the retrieval set, IJIP still reaches up to 89.2% accuracy. With complete labels, it scores 86.4%, which the authors report as SOTA.
- As a plug-in on SST5 with LLaMA 3.1 8B, IJIP lifts CD by 4.6 points and DKNN by 5.2 points on average. Across zero-shot and ICL methods, the average gain is 4.9%.
- On CIFAR-10, IJIP outperforms the zero-shot CLIP baseline (88.7%) with every InternVL size tested.
- Cost on SST5:
  - Cutting demonstrations from 10 to 5 loses only 1.2 accuracy points and reduces usage to 174.3 tokens and 0.38 s per text.
  - The training-based variant needs 20.3 minutes of training and 468 MB of storage.

*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

- [Sun Yat-sen University](https://md.research.elamur.ai/free/en/universities/sun-yat-sen-university/) — University, Guangzhou, China · 53 works · 9,185 citations
- [Peng Cheng Laboratory](https://md.research.elamur.ai/free/en/labs/peng-cheng-laboratory/) — Research institute, Shenzhen, China · 38 works · 2,504 citations
- [Lanzhou University](https://md.research.elamur.ai/free/en/universities/lanzhou-university/) — University, Lanzhou, China · 5 works · 24 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works

🧭 Topics (1): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,320 works

## Cite

Cite as: Wenqiang Wang, Wen Yujia, Yan Xiao, Zhifeng Chen, Yangshijie Zhang, Peng Chen, Mingbo Yang and Xiaochun Cao. 2026. Incomplete In-context Learning. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

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

```bibtex
@inproceedings{wang2026incomplete,
  title = {{Incomplete In-context Learning}},
  author = {Wenqiang Wang, Wen Yujia, Yan Xiao, Zhifeng Chen, Yangshijie Zhang, Peng Chen, Mingbo Yang and Xiaochun Cao},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.1931},
  url = {https://doi.org/10.18653/v1/2026.acl-long.1931}
}
```

- [← previous In-Context Representation Hijacking](https://md.research.elamur.ai/free/en/papers/yona-2026-context-representation-hijacking/)
- [next → InsightEval: An Expert-Curated Benchmark for Assessing Insight Discovery in LLM-Driven Data Agents](https://md.research.elamur.ai/free/en/papers/zhu-2026-insighteval-expert-curated-benchmark-assessing/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/7/)

## References

100 references, 23 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Yehya Abouelnaga, Ola S Ali, Hager Rady, and Mohamed Moustafa. 2016. Cifar-10: Knn-based ensemble of classifiers. In 2016 International Conference on Computational Science and Computational Intelligence (CSCI), pages 1192–1195. IEEE. [find](https://scholar.google.com/scholar?q=Yehya+Abouelnaga%2C+Ola+S+Ali%2C+Hager+Rady%2C+and+Mohamed+Moustafa%2E+2016%2E+Cifar%2D10%3A+Knn%2Dbased+ensemble+of+classifiers%2E+In+2016+International+Conference+on+Computational+Science+and+Computational+Intelligen)
2. Farhad Akhbardeh, Cecilia Ovesdotter Alm, Marcos Zampieri, and Travis Desell. 2021. Handling extreme class imbalance in technical logbook datasets. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Langua… [find](https://scholar.google.com/scholar?q=Farhad+Akhbardeh%2C+Cecilia+Ovesdotter+Alm%2C+Marcos+Zampieri%2C+and+Travis+Desell%2E+2021%2E+Handling+extreme+class+imbalance+in+technical+logbook+datasets%2E+In+Proceedings+of+the+59th+Annual+Meeting+of+the+Ass)
3. Josh Attenberg and Foster Provost. 2010. Why label when you can search? alternatives to active learning for applying human resources to build classification models under extreme class imbalance. In Proceedings of the 16th ACM SIGKDD international conference on Knowledge discovery and data mining, pa… [find](https://scholar.google.com/scholar?q=Josh+Attenberg+and+Foster+Provost%2E+2010%2E+Why+label+when+you+can+search%3F+alternatives+to+active+learning+for+applying+human+resources+to+build+classification+models+under+extreme+class+imbalance%2E+In+Pr)
4. Jack Bell, Luigi Quarantiello, Eric Nuertey Coleman, Lanpei Li, Mauro Madeddu, and Vincenzo Lomonaco. 2025. The future of continual learning in the era of foundation models: Three key directions. arXiv preprint. [find](https://scholar.google.com/scholar?q=Jack+Bell%2C+Luigi+Quarantiello%2C+Eric+Nuertey+Coleman%2C+Lanpei+Li%2C+Mauro+Madeddu%2C+and+Vincenzo+Lomonaco%2E+2025%2E+The+future+of+continual+learning+in+the+era+of+foundation+models%3A+Three+key+directions%2E+arXi)
5. Amanda Bertsch, Maor Ivgi, Emily Xiao, Uri Alon, Jonathan Berant, Matthew R. Gormley, and Graham Neubig. 2025. [In-context learning with long-context models: An in-depth exploration](https://md.research.elamur.ai/free/en/papers/bertsch-2025-context-learning-long-context-models/). In Proceedings of the 2025 Conference of the North American Chapter of the Association for Computational Linguistics:…
6. Samuel R Bowman, Gabor Angeli, Christopher Potts, and Christopher D Manning. 2015. [A large annotated corpus for learning natural language inference](https://md.research.elamur.ai/free/en/papers/bowman-2015-large-annotated-corpus-learning-natural/). In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 632– 642.
7. Xusheng Cao, Haori Lu, Xialei Liu, and Ming-Ming Cheng. 2025. Class incremental learning for image classification with out-of-distribution task identification. IEEE Transactions on Multimedia. [find](https://scholar.google.com/scholar?q=Xusheng+Cao%2C+Haori+Lu%2C+Xialei+Liu%2C+and+Ming%2DMing+Cheng%2E+2025%2E+Class+incremental+learning+for+image+classification+with+out%2Dof%2Ddistribution+task+identification%2E+IEEE+Transactions+on+Multimedia%2E)
8. Zhe Chen, Jiannan Wu, Wenhai Wang, Weijie Su, Guo Chen, Sen Xing, Muyan Zhong, Qinglong Zhang, Xizhou Zhu, Lewei Lu, and 1 others. 2024. [Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks](https://md.research.elamur.ai/free/en/papers/chen-2023-internvl-scaling-up-vision/). In Proceedings of the IEEE/CVF conference on computer vision and pa…
9. Chen Cheng, Xinzhi Yu, Haodong Wen, Jinsong Sun, Guanzhang Yue, Yihao Zhang, and Zeming Wei. 2024. Exploring the robustness of in-context learning with noisy labels. arXiv preprint arXiv:2404.18191. — [arXiv:2404.18191](https://arxiv.org/abs/2404.18191) [find](https://scholar.google.com/scholar?q=Chen+Cheng%2C+Xinzhi+Yu%2C+Haodong+Wen%2C+Jinsong+Sun%2C+Guanzhang+Yue%2C+Yihao+Zhang%2C+and+Zeming+Wei%2E+2024%2E+Exploring+the+robustness+of+in%2Dcontext+learning+with+noisy+labels%2E+arXiv+preprint+arXiv%3A2404%2E18191%2E+%E2%80%94)
10. Jiawei Dai, Hanxiao Liu, Yizhou Wang, and Hongyu Wu. 2023. Promptagator: Fine-tuning retrieval models with contrastive learning for better in-context learning. arXiv preprint arXiv:2304.05744. — [arXiv:2304.05744](https://arxiv.org/abs/2304.05744) [find](https://scholar.google.com/scholar?q=Jiawei+Dai%2C+Hanxiao+Liu%2C+Yizhou+Wang%2C+and+Hongyu+Wu%2E+2023%2E+Promptagator%3A+Fine%2Dtuning+retrieval+models+with+contrastive+learning+for+better+in%2Dcontext+learning%2E+arXiv+preprint+arXiv%3A2304%2E05744%2E+%E2%80%94+%5BarXi)
11. Alexander de Wynter. 2025. Is in-context learning learning? arXiv preprint. [find](https://scholar.google.com/scholar?q=Alexander+de+Wynter%2E+2025%2E+Is+in%2Dcontext+learning+learning%3F+arXiv+preprint%2E)
12. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. [Bert: Pre-training of deep bidirectional transformers for language understanding](https://md.research.elamur.ai/free/en/papers/devlin-2019-bert-pre-training-deep-bidirectional/). In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,…
13. Benjamin Dherin. 2025. The implicit dynamics of in-context learning. arXiv preprint. [find](https://scholar.google.com/scholar?q=Benjamin+Dherin%2E+2025%2E+The+implicit+dynamics+of+in%2Dcontext+learning%2E+arXiv+preprint%2E)
14. Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. [An image is worth 16x16 words: Transformers for image recognition at scale](https://md.research.elamur.ai/free/en/papers/dosovitskiy-2020-image-worth-16x16-words-transformers/). In 9th In…
15. Yu Fei, Yifan Hou, Zeming Chen, and Antoine Bosselut. 2023. [Mitigating label biases for in-context learning](https://md.research.elamur.ai/free/en/papers/fei-2023-mitigating-label-biases-context-learning/). In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 14014–14031.
16. Yao Fu, Hao Peng, Ashish Sabharwal, Peter Clark, and Tushar Khot. 2023. [Complexity-based prompting for multi-step reasoning](https://md.research.elamur.ai/free/en/papers/fu-2022-complexity-based-prompting-multi-step/). In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net.
17. Zhiwei Gao and 1 others. 2025. Knowledge memorization and rumination for pre-trained model-based class-incremental learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2025. [find](https://scholar.google.com/scholar?q=Zhiwei+Gao+and+1+others%2E+2025%2E+Knowledge+memorization+and+rumination+for+pre%2Dtrained+model%2Dbased+class%2Dincremental+learning%2E+In+Proceedings+of+the+IEEE%2FCVF+Conference+on+Computer+Vision+and+Pattern+Re)
18. Manoj Garg and 1 others. 2022. Meta-learning for in-context learning tasks. ICLR. Available at [https://openreview.net/forum?id=Z2MavhD8bt](https://openreview.net/forum?id=Z2MavhD8bt). [↗](https://openreview.net/forum?id=Z2MavhD8bt)
19. Hila Gonen, Srini Iyer, Terra Blevins, Noah A Smith, and Luke Zettlemoyer. 2023. Demystifying prompts in language models via perplexity estimation. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 10136–10148. [find](https://scholar.google.com/scholar?q=Hila+Gonen%2C+Srini+Iyer%2C+Terra+Blevins%2C+Noah+A+Smith%2C+and+Luke+Zettlemoyer%2E+2023%2E+Demystifying+prompts+in+language+models+via+perplexity+estimation%2E+In+Findings+of+the+Association+for+Computational+Lin)
20. Karan Gupta, Sumegh Roychowdhury, Siva Rajesh Kasa, Santhosh Kumar Kasa, Anish Bhanushali, Nikhil Pattisapu, and Prasanna Srinivasa Murthy. 2023. How robust are llms to in-context majority label bias? arXiv preprint arXiv:2312.16549. — [arXiv:2312.16549](https://arxiv.org/abs/2312.16549) [find](https://scholar.google.com/scholar?q=Karan+Gupta%2C+Sumegh+Roychowdhury%2C+Siva+Rajesh+Kasa%2C+Santhosh+Kumar+Kasa%2C+Anish+Bhanushali%2C+Nikhil+Pattisapu%2C+and+Prasanna+Srinivasa+Murthy%2E+2023%2E+How+robust+are+llms+to+in%2Dcontext+majority+label+bias%3F)
21. Guo Haixiang, Li Yijing, Jennifer Shang, Gu Mingyun, Huang Yuanyue, and Gong Bing. 2017. Learning from class-imbalanced data: Review of methods and applications. Expert systems with applications, 73:220–239. [find](https://scholar.google.com/scholar?q=Guo+Haixiang%2C+Li+Yijing%2C+Jennifer+Shang%2C+Gu+Mingyun%2C+Huang+Yuanyue%2C+and+Gong+Bing%2E+2017%2E+Learning+from+class%2Dimbalanced+data%3A+Review+of+methods+and+applications%2E+Expert+systems+with+applications%2C+73%3A2)
22. Zheng Yi Ho, Siyuan Liang, Sen Zhang, Yibing Zhan, and Dacheng Tao. 2024. Novo: Norm voting off hallucinations with attention heads in large language models. arXiv preprint arXiv:2410.08970. — [arXiv:2410.08970](https://arxiv.org/abs/2410.08970) [find](https://scholar.google.com/scholar?q=Zheng+Yi+Ho%2C+Siyuan+Liang%2C+Sen+Zhang%2C+Yibing+Zhan%2C+and+Dacheng+Tao%2E+2024%2E+Novo%3A+Norm+voting+off+hallucinations+with+attention+heads+in+large+language+models%2E+arXiv+preprint+arXiv%3A2410%2E08970%2E+%E2%80%94+%5BarXiv%3A)
23. Fanding Huang, Guanbo Huang, Xiao Fan, Yi He, Xiao Liang, Xiao Chen, Qinting Jiang, Faisal Nadeem Khan, Jingyan Jiang, and Zhi Wang. 2026. Semantic-space exploration and exploitation in rlvr for llm reasoning. Preprint, arXiv:2509.23808. [find](https://scholar.google.com/scholar?q=Fanding+Huang%2C+Guanbo+Huang%2C+Xiao+Fan%2C+Yi+He%2C+Xiao+Liang%2C+Xiao+Chen%2C+Qinting+Jiang%2C+Faisal+Nadeem+Khan%2C+Jingyan+Jiang%2C+and+Zhi+Wang%2E+2026%2E+Semantic%2Dspace+exploration+and+exploitation+in+rlvr+for+llm+r)
24. Fanding Huang, Jingyan Jiang, Qinting Jiang, Hebei Li, Faisal Nadeem Khan, and Zhi Wang. 2025. Cosmic: Clique-oriented semantic multi-space integration for robust clip test-time adaptation. In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 9772–9781. [find](https://scholar.google.com/scholar?q=Fanding+Huang%2C+Jingyan+Jiang%2C+Qinting+Jiang%2C+Hebei+Li%2C+Faisal+Nadeem+Khan%2C+and+Zhi+Wang%2E+2025%2E+Cosmic%3A+Clique%2Doriented+semantic+multi%2Dspace+integration+for+robust+clip+test%2Dtime+adaptation%2E+In+Proceed)
25. Quentin Jodelet and 1 others. 2025. Future-proofing class-incremental learning. Machine Vision and Applications (Springer) / special issue 2025. [find](https://scholar.google.com/scholar?q=Quentin+Jodelet+and+1+others%2E+2025%2E+Future%2Dproofing+class%2Dincremental+learning%2E+Machine+Vision+and+Applications+%28Springer%29+%2F+special+issue+2025%2E)
26. David Minkwan Kim, Soeun Lee, and Byeongkeun Kang. 2025. Completely weakly supervised class-incremental learning for semantic segmentation. arXiv preprint. [find](https://scholar.google.com/scholar?q=David+Minkwan+Kim%2C+Soeun+Lee%2C+and+Byeongkeun+Kang%2E+2025%2E+Completely+weakly+supervised+class%2Dincremental+learning+for+semantic+segmentation%2E+arXiv+preprint%2E)
27. Jannik Kossen, Yarin Gal, and Tom Rainforth. 2024. In-context learning learns label relationships but is not conventional learning. In International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Jannik+Kossen%2C+Yarin+Gal%2C+and+Tom+Rainforth%2E+2024%2E+In%2Dcontext+learning+learns+label+relationships+but+is+not+conventional+learning%2E+In+International+Conference+on+Learning+Representations%2E)
28. Alex Krizhevsky, Geoffrey Hinton, and 1 others. 2009. Learning multiple layers of features from tiny images. [find](https://scholar.google.com/scholar?q=Alex+Krizhevsky%2C+Geoffrey+Hinton%2C+and+1+others%2E+2009%2E+Learning+multiple+layers+of+features+from+tiny+images%2E)
29. Atsutoshi Kumagai, Tomoharu Iwata, Hiroshi Takahashi, Taishi Nishiyama, and Yasuhiro Fujiwara. 2025. Importance-weighted positive–unlabeled learning for distribution shift adaptation. In Proceedings of the 2025 International Conference on Artificial Intelligence and Statistics (AISTATS 2025). [find](https://scholar.google.com/scholar?q=Atsutoshi+Kumagai%2C+Tomoharu+Iwata%2C+Hiroshi+Takahashi%2C+Taishi+Nishiyama%2C+and+Yasuhiro+Fujiwara%2E+2025%2E+Importance%2Dweighted+positive%E2%80%93unlabeled+learning+for+distribution+shift+adaptation%2E+In+Proceedings+o)
30. Vishnuprasadh Kumaravelu, P.K. Srijith, and Sunil Gupta. 2025. Evocl: Continual learning over evolving domains. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2025). [find](https://scholar.google.com/scholar?q=Vishnuprasadh+Kumaravelu%2C+P%2EK%2E+Srijith%2C+and+Sunil+Gupta%2E+2025%2E+Evocl%3A+Continual+learning+over+evolving+domains%2E+In+Proceedings+of+the+IEEE%2FCVF+Winter+Conference+on+Applications+of+Computer+Vision+%28WAC)
31. Chuyuan Li, Raymond Li, Thalia S. Field, and Giuseppe Carenini. 2025a. Delta-knn: Improving demonstration selection in in-context learning for alzheimer’s disease detection. In Proceedings of the 2025 Annual Meeting of the Association for Computational Linguistics (ACL 2025) — Long Papers. [find](https://scholar.google.com/scholar?q=Chuyuan+Li%2C+Raymond+Li%2C+Thalia+S%2E+Field%2C+and+Giuseppe+Carenini%2E+2025a%2E+Delta%2Dknn%3A+Improving+demonstration+selection+in+in%2Dcontext+learning+for+alzheimer%E2%80%99s+disease+detection%2E+In+Proceedings+of+the+2025)
32. ACL 2025; PDF available on ACL Anthology. [find](https://scholar.google.com/scholar?q=ACL+2025%3B+PDF+available+on+ACL+Anthology%2E)
33. Chuyuan Li, Raymond Li, Thalia S Field, and Giuseppe Carenini. 2025b. Delta-knn: Improving demonstration selection in in-context learning for alzheimer’s disease detection. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3873–… [find](https://scholar.google.com/scholar?q=Chuyuan+Li%2C+Raymond+Li%2C+Thalia+S+Field%2C+and+Giuseppe+Carenini%2E+2025b%2E+Delta%2Dknn%3A+Improving+demonstration+selection+in+in%2Dcontext+learning+for+alzheimer%E2%80%99s+disease+detection%2E+In+Proceedings+of+the+63rd+)
34. Dongliang Li, Yuqiang Liu, Yichao Lu, and Wenxin Zhang. 2023. Contextualizing retrieval-augmented in-context learning: Diversity and retrieval. arXiv preprint arXiv:2303.06334. — [arXiv:2303.06334](https://arxiv.org/abs/2303.06334) [find](https://scholar.google.com/scholar?q=Dongliang+Li%2C+Yuqiang+Liu%2C+Yichao+Lu%2C+and+Wenxin+Zhang%2E+2023%2E+Contextualizing+retrieval%2Daugmented+in%2Dcontext+learning%3A+Diversity+and+retrieval%2E+arXiv+preprint+arXiv%3A2303%2E06334%2E+%E2%80%94+%5BarXiv%3A2303%2E06334%5D%28ht)
35. Qiongxiu Li, Xiaoyu Luo, Yiyi Chen, and Johannes Bjerva. 2025c. Trustworthy machine learning via memorization and the granular long-tail: A survey on interactions, tradeoffs, and beyond. arXiv preprint. 2025 survey linking memorization and long-tail phenomena; long-tail . [find](https://scholar.google.com/scholar?q=Qiongxiu+Li%2C+Xiaoyu+Luo%2C+Yiyi+Chen%2C+and+Johannes+Bjerva%2E+2025c%2E+Trustworthy+machine+learning+via+memorization+and+the+granular+long%2Dtail%3A+A+survey+on+interactions%2C+tradeoffs%2C+and+beyond%2E+arXiv+preprin)
36. Shuo Li, Fang Liu, Licheng Jiac, Lingling Li, Puhua Chen, Xu Liu, and Wenping Ma. 2025d. Prompt-based concept learning for few-shot class-incremental learning. IEEE Transactions on Circuits and Systems for Video Technology. [find](https://scholar.google.com/scholar?q=Shuo+Li%2C+Fang+Liu%2C+Licheng+Jiac%2C+Lingling+Li%2C+Puhua+Chen%2C+Xu+Liu%2C+and+Wenping+Ma%2E+2025d%2E+Prompt%2Dbased+concept+learning+for+few%2Dshot+class%2Dincremental+learning%2E+IEEE+Transactions+on+Circuits+and+System)
37. Tianle Li and 1 others. 2024a. Longiclbench: [Long-context llms struggle with long in-context learning](https://md.research.elamur.ai/free/en/papers/li-2024-long-context-llms-struggle-long/). Arxiv Preprint. Available at [https://arxiv.org/](https://arxiv.org/) abs/2402.04024. [↗](https://arxiv.org/)
38. Wen Li, Yihan Liu, Hao Chen, and Xin Zhang. 2025e. Explanation-based in-context demonstrations retrieval. arXiv preprint. [find](https://scholar.google.com/scholar?q=Wen+Li%2C+Yihan+Liu%2C+Hao+Chen%2C+and+Xin+Zhang%2E+2025e%2E+Explanation%2Dbased+in%2Dcontext+demonstrations+retrieval%2E+arXiv+preprint%2E)
39. Xiao-Li Li, Philip S Yu, Bing Liu, and See-Kiong Ng. 2009. Positive unlabeled learning for data stream classification. In Proceedings of the 2009 SIAM international conference on data mining, pages 259–270. SIAM. [find](https://scholar.google.com/scholar?q=Xiao%2DLi+Li%2C+Philip+S+Yu%2C+Bing+Liu%2C+and+See%2DKiong+Ng%2E+2009%2E+Positive+unlabeled+learning+for+data+stream+classification%2E+In+Proceedings+of+the+2009+SIAM+international+conference+on+data+mining%2C+pages+25)
40. Xiaonan Li and Xipeng Qiu. 2023a. [Finding support examples for in-context learning](https://md.research.elamur.ai/free/en/papers/li-2023-finding-support-examples-context-learning/). In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 6219–6235.
41. Xiaonan Li and Xipeng Qiu. 2023b. Mot: Pre-thinking and recalling enable chatgpt to self-improve with memory-of-thoughts. CoRR. [find](https://scholar.google.com/scholar?q=Xiaonan+Li+and+Xipeng+Qiu%2E+2023b%2E+Mot%3A+Pre%2Dthinking+and+recalling+enable+chatgpt+to+self%2Dimprove+with+memory%2Dof%2Dthoughts%2E+CoRR%2E)
42. Xiping Li, Xiangyu Dong, Xingyi Zhang, Kun Xie, Yuanhao Feng, Bo Wang, Guilin Li, Wuxiong Zeng, Xiujun Shu, and Sibo Wang. 2025f. Chi-square wavelet graph neural networks for heterogeneous graph anomaly detection. In Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Minin… [find](https://scholar.google.com/scholar?q=Xiping+Li%2C+Xiangyu+Dong%2C+Xingyi+Zhang%2C+Kun+Xie%2C+Yuanhao+Feng%2C+Bo+Wang%2C+Guilin+Li%2C+Wuxiong+Zeng%2C+Xiujun+Shu%2C+and+Sibo+Wang%2E+2025f%2E+Chi%2Dsquare+wavelet+graph+neural+networks+for+heterogeneous+graph+anoma)
43. Xiping Li and Jianghong Ma. 2026. Aim-cot: Active information-driven multimodal chain-of-thought for vision-language reasoning. Preprint, arXiv:2509.25699. [find](https://scholar.google.com/scholar?q=Xiping+Li+and+Jianghong+Ma%2E+2026%2E+Aim%2Dcot%3A+Active+information%2Ddriven+multimodal+chain%2Dof%2Dthought+for+vision%2Dlanguage+reasoning%2E+Preprint%2C+arXiv%3A2509%2E25699%2E)
44. Xiping Li, Jianghong Ma, Kangzhe Liu, Shanshan Feng, Haijun Zhang, and Yutong Wang. 2024b. Category-based and popularity-guided video game recommendation: a balance-oriented framework. In Proceedings of the ACM Web Conference 2024, pages 3734– 3744. [find](https://scholar.google.com/scholar?q=Xiping+Li%2C+Jianghong+Ma%2C+Kangzhe+Liu%2C+Shanshan+Feng%2C+Haijun+Zhang%2C+and+Yutong+Wang%2E+2024b%2E+Category%2Dbased+and+popularity%2Dguided+video+game+recommendation%3A+a+balance%2Doriented+framework%2E+In+Proceedings+)
45. Xiping Li, Aier Yang, Jianghong Ma, Kangzhe Liu, Shanshan Feng, Haijun Zhang, and Yi Zhao. 2026. Cpgrec+: A balance-oriented framework for personalized video game recommendations. ACM Transactions on Information Systems, 44(3):1–44. [find](https://scholar.google.com/scholar?q=Xiping+Li%2C+Aier+Yang%2C+Jianghong+Ma%2C+Kangzhe+Liu%2C+Shanshan+Feng%2C+Haijun+Zhang%2C+and+Yi+Zhao%2E+2026%2E+Cpgrec%2B%3A+A+balance%2Doriented+framework+for+personalized+video+game+recommendations%2E+ACM+Transactions+on+)
46. Ziqian Lin and Kangwook Lee. 2024. Dual operating modes of in-context learning. ICLR. Available at [https://openreview.net/forum?id=](https://openreview.net/forum?id=) HkAtRP9cOY. [↗](https://openreview.net/forum?id=)
47. Lei Mao, Yuqiang Yang, Qi Wei, and Zhiwei Chen. 2024. A survey on data generation and task learning in in-context learning. arXiv preprint arXiv:2403.06201. — [arXiv:2403.06201](https://arxiv.org/abs/2403.06201) [find](https://scholar.google.com/scholar?q=Lei+Mao%2C+Yuqiang+Yang%2C+Qi+Wei%2C+and+Zhiwei+Chen%2E+2024%2E+A+survey+on+data+generation+and+task+learning+in+in%2Dcontext+learning%2E+arXiv+preprint+arXiv%3A2403%2E06201%2E+%E2%80%94+%5BarXiv%3A2403%2E06201%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F)
48. Aishan Liu, Yuguang Zhou, Xianglong Liu, Tianyuan Zhang, Siyuan Liang, Jiakai Wang, Yanjun Pu, Tianlin Li, Junqi Zhang, Wenbo Zhou, and 1 others. 2024a. Compromising embodied agents with contextual backdoor attacks. arXiv preprint arXiv:2408.02882. — [arXiv:2408.02882](https://arxiv.org/abs/2408.02882) [find](https://scholar.google.com/scholar?q=Aishan+Liu%2C+Yuguang+Zhou%2C+Xianglong+Liu%2C+Tianyuan+Zhang%2C+Siyuan+Liang%2C+Jiakai+Wang%2C+Yanjun+Pu%2C+Tianlin+Li%2C+Junqi+Zhang%2C+Wenbo+Zhou%2C+and+1+others%2E+2024a%2E+Compromising+embodied+agents+with+contextual+ba)
49. Daniel Mildenberger, Junjie Fang, and Yongming Xu. 2025. A tale of two classes: Adapting supervised contrastive strategies for imbalanced binary classification. In Proceedings of NeurIPS 2025. [find](https://scholar.google.com/scholar?q=Daniel+Mildenberger%2C+Junjie+Fang%2C+and+Yongming+Xu%2E+2025%2E+A+tale+of+two+classes%3A+Adapting+supervised+contrastive+strategies+for+imbalanced+binary+classification%2E+In+Proceedings+of+NeurIPS+2025%2E)
50. Hui Liu, Wenya Wang, Hao Sun, Chris Xing Tian, Chenqi Kong, Xin Dong, and Haoliang Li. 2025a. [Unraveling the mechanics of learning-based demonstration selection for in-context learning](https://md.research.elamur.ai/free/en/papers/liu-2025-unraveling-mechanics-learning-based-demonstration/). In Association for Computational Linguistics 2025.
51. Jiachang Liu, Dinghan Shen, Yizhe Zhang, William B Dolan, Lawrence Carin, and Weizhu Chen. 2022. [What makes good in-context examples for gpt-3?](https://md.research.elamur.ai/free/en/papers/liu-2022-what-makes-good-context-examples/) In Proceedings of Deep Learning Inside Out (Dee-LIO 2022): The 3rd Workshop on Knowledge Extraction and Integration for Deep Learning Architectures, pages 1…
52. Wenzhuo Liu, Xin-Jian Wu, Fei Zhu, Ming-Ming Yu, Chuang Wang, and Cheng-Lin Liu. 2025b. Class incremental learning with self-supervised pre-training and prototype learning. Pattern Recognition, 157:110943. [find](https://scholar.google.com/scholar?q=Wenzhuo+Liu%2C+Xin%2DJian+Wu%2C+Fei+Zhu%2C+Ming%2DMing+Yu%2C+Chuang+Wang%2C+and+Cheng%2DLin+Liu%2E+2025b%2E+Class+incremental+learning+with+self%2Dsupervised+pre%2Dtraining+and+prototype+learning%2E+Pattern+Recognition%2C+157%3A11)
53. Yinpeng Liu, Jiawei Liu, Xiang Shi, Qikai Cheng, Yong Huang, and Wei Lu. 2024b. Let’s learn step by step: Enhancing in-context learning ability with curriculum learning. arXiv preprint arXiv:2402.10738. — [arXiv:2402.10738](https://arxiv.org/abs/2402.10738) [find](https://scholar.google.com/scholar?q=Yinpeng+Liu%2C+Jiawei+Liu%2C+Xiang+Shi%2C+Qikai+Cheng%2C+Yong+Huang%2C+and+Wei+Lu%2E+2024b%2E+Let%E2%80%99s+learn+step+by+step%3A+Enhancing+in%2Dcontext+learning+ability+with+curriculum+learning%2E+arXiv+preprint+arXiv%3A2402%2E1073)
54. Yu Liu and 1 others. 2025c. Sec-prompts: Semantic complementary prompting for few-shot class-incremental learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2025. [find](https://scholar.google.com/scholar?q=Yu+Liu+and+1+others%2E+2025c%2E+Sec%2Dprompts%3A+Semantic+complementary+prompting+for+few%2Dshot+class%2Dincremental+learning%2E+In+Proceedings+of+the+IEEE%2FCVF+Conference+on+Computer+Vision+and+Pattern+Recognition+)
55. Yao Lu, Max Bartolo, Alastair Moore, Sebastian Riedel, and Pontus Stenetorp. 2022. [Fantastically ordered prompts and where to find them: Overcoming few-shot prompt order sensitivity](https://md.research.elamur.ai/free/en/papers/lu-2022-fantastically-ordered-prompts-where-find/). In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), p…
56. Shuang Luo, Linjun Shou, Shuming Ma, Jiawei Liu, and Zhiwei Zhang. 2024. In-context learning with retrieval: A survey. arXiv preprint arXiv:2401.06247. — [arXiv:2401.06247](https://arxiv.org/abs/2401.06247) [find](https://scholar.google.com/scholar?q=Shuang+Luo%2C+Linjun+Shou%2C+Shuming+Ma%2C+Jiawei+Liu%2C+and+Zhiwei+Zhang%2E+2024%2E+In%2Dcontext+learning+with+retrieval%3A+A+survey%2E+arXiv+preprint+arXiv%3A2401%2E06247%2E+%E2%80%94+%5BarXiv%3A2401%2E06247%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2401%2E)
57. Xinxi Lyu, Sewon Min, Iz Beltagy, Luke Zettlemoyer, and Hannaneh Hajishirzi. 2023. Z-ICL: Zero-shot in-context learning with pseudo-demonstrations. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2304–2317. [find](https://scholar.google.com/scholar?q=Xinxi+Lyu%2C+Sewon+Min%2C+Iz+Beltagy%2C+Luke+Zettlemoyer%2C+and+Hannaneh+Hajishirzi%2E+2023%2E+Z%2DICL%3A+Zero%2Dshot+in%2Dcontext+learning+with+pseudo%2Ddemonstrations%2E+In+Proceedings+of+the+61st+Annual+Meeting+of+the+Ass)
58. Farhad Mansouri, Xiaotian Liu, and Sanghyun Park. 2025. Learning from positive and unlabeled examples: Finite-sample complexity and bounds. arXiv preprint. [find](https://scholar.google.com/scholar?q=Farhad+Mansouri%2C+Xiaotian+Liu%2C+and+Sanghyun+Park%2E+2025%2E+Learning+from+positive+and+unlabeled+examples%3A+Finite%2Dsample+complexity+and+bounds%2E+arXiv+preprint%2E)
59. Sewon Min, Xinxi Lyu, Ari Holtzman, Mikel Artetxe, Mike Lewis, Hannaneh Hajishirzi, and Luke Zettlemoyer. 2022. [Rethinking the role of demonstrations: What makes in-context learning work?](https://md.research.elamur.ai/free/en/papers/min-2022-rethinking-role-demonstrations-what-makes/) In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 11048–11064.
60. Saleh Momeni, Sahisnu Mazumder, Zixuan Ke, and Bing Liu. 2025. Inca: In-context continual learning assisted by an external continual learner. In Proceedings of COLING 2025. [find](https://scholar.google.com/scholar?q=Saleh+Momeni%2C+Sahisnu+Mazumder%2C+Zixuan+Ke%2C+and+Bing+Liu%2E+2025%2E+Inca%3A+In%2Dcontext+continual+learning+assisted+by+an+external+continual+learner%2E+In+Proceedings+of+COLING+2025%2E)
61. Arman Nafar, Jun Chen, Daniel Khashabi, and Dan Roth. 2025. Learning vs retrieval: The role of in-context examples in large language models. In Proceedings of the 2025 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2025). [find](https://scholar.google.com/scholar?q=Arman+Nafar%2C+Jun+Chen%2C+Daniel+Khashabi%2C+and+Dan+Roth%2E+2025%2E+Learning+vs+retrieval%3A+The+role+of+in%2Dcontext+examples+in+large+language+models%2E+In+Proceedings+of+the+2025+Conference+of+the+North+American)
62. Ranjita Naik, Varun Chandrasekaran, Mert Yuksekgonul, Hamid Palangi, and Besmira Nushi. 2023. Diversity of thought improves reasoning abilities of large language models. [find](https://scholar.google.com/scholar?q=Ranjita+Naik%2C+Varun+Chandrasekaran%2C+Mert+Yuksekgonul%2C+Hamid+Palangi%2C+and+Besmira+Nushi%2E+2023%2E+Diversity+of+thought+improves+reasoning+abilities+of+large+language+models%2E)
63. Milad Khademi Nori, Il-Min Kim, and Guanghui Wang. 2025. Autoencoder-based hybrid replay for class-incremental learning. arXiv preprint. [find](https://scholar.google.com/scholar?q=Milad+Khademi+Nori%2C+Il%2DMin+Kim%2C+and+Guanghui+Wang%2E+2025%2E+Autoencoder%2Dbased+hybrid+replay+for+class%2Dincremental+learning%2E+arXiv+preprint%2E)
64. Ziqian Pan and 1 others. 2023. Dual operating modes of in-context learning. ICML, pages 2345–2356. [find](https://scholar.google.com/scholar?q=Ziqian+Pan+and+1+others%2E+2023%2E+Dual+operating+modes+of+in%2Dcontext+learning%2E+ICML%2C+pages+2345%E2%80%932356%2E)
65. Guang Peng, Kai Zhang, and Weijia Zhao. 2025. Encode errors: Representational retrieval of in-context information. In Findings of the Association for Computational Linguistics 2025. [find](https://scholar.google.com/scholar?q=Guang+Peng%2C+Kai+Zhang%2C+and+Weijia+Zhao%2E+2025%2E+Encode+errors%3A+Representational+retrieval+of+in%2Dcontext+information%2E+In+Findings+of+the+Association+for+Computational+Linguistics+2025%2E)
66. Kha Pham, Hung Le, Man Ngo, and Truyen Tran. 2025. Rapid selection and ordering of in-context demonstrations via prompt embedding clustering. In Proceedings of the International Conference on Learning Representations (ICLR) 2025. [find](https://scholar.google.com/scholar?q=Kha+Pham%2C+Hung+Le%2C+Man+Ngo%2C+and+Truyen+Tran%2E+2025%2E+Rapid+selection+and+ordering+of+in%2Dcontext+demonstrations+via+prompt+embedding+clustering%2E+In+Proceedings+of+the+International+Conference+on+Learning)
67. ICLR 2025 poster / paper; OpenReview PDF available. [find](https://scholar.google.com/scholar?q=ICLR+2025+poster+%2F+paper%3B+OpenReview+PDF+available%2E)
68. Kiran Purohit, V. Venktesh, Sourangshu Bhattacharya, and Avishek Anand. 2025. Sample efficient demonstration selection for in-context learning. In Proceedings of the 2025 International Conference on Machine Learning (ICML 2025). [find](https://scholar.google.com/scholar?q=Kiran+Purohit%2C+V%2E+Venktesh%2C+Sourangshu+Bhattacharya%2C+and+Avishek+Anand%2E+2025%2E+Sample+efficient+demonstration+selection+for+in%2Dcontext+learning%2E+In+Proceedings+of+the+2025+International+Conference+on+M)
69. ICML 2025; preprint on arXiv:2506.08607. — [arXiv:2506.08607](https://arxiv.org/abs/2506.08607) [find](https://scholar.google.com/scholar?q=ICML+2025%3B+preprint+on+arXiv%3A2506%2E08607%2E+%E2%80%94+%5BarXiv%3A2506%2E08607%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2506%2E08607%29)
70. Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021a. [Learning transferable visual models from natural language supervision](https://md.research.elamur.ai/free/en/papers/radford-2021-learning-transferable-visual-models-natural/). In Proceedings of the 38th Internati…
71. Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, and 1 others. 2021b. [Learning transferable visual models from natural language supervision](https://md.research.elamur.ai/free/en/papers/radford-2021-learning-transferable-visual-models-natural/). In International conference on machine learning, pages 8748–…
72. Alec Radford, Karthik Narasimhan, Tim Salimans, Ilya Sutskever, and 1 others. 2018. Improving language understanding by generative pre-training. [find](https://scholar.google.com/scholar?q=Alec+Radford%2C+Karthik+Narasimhan%2C+Tim+Salimans%2C+Ilya+Sutskever%2C+and+1+others%2E+2018%2E+Improving+language+understanding+by+generative+pre%2Dtraining%2E)
73. Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, Ilya Sutskever, and 1 others. 2019. Language models are unsupervised multitask learners. OpenAI blog, 1(8):9. [find](https://scholar.google.com/scholar?q=Alec+Radford%2C+Jeffrey+Wu%2C+Rewon+Child%2C+David+Luan%2C+Dario+Amodei%2C+Ilya+Sutskever%2C+and+1+others%2E+2019%2E+Language+models+are+unsupervised+multitask+learners%2E+OpenAI+blog%2C+1%288%29%3A9%2E)
74. Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2020a. [Exploring the limits of transfer learning with a unified text-to-text transformer](https://md.research.elamur.ai/free/en/papers/raffel-2019-exploring-limits-transfer-learning-unified/). J. Mach. Learn. Res., 21:140:1–140:67.
75. Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2020b. [Exploring the limits of transfer learning with a unified text-to-text transformer](https://md.research.elamur.ai/free/en/papers/raffel-2019-exploring-limits-transfer-learning-unified/). Journal of Machine Learning Research, 21(140):1–67.
76. Vasilii Rubin, Nikolaos Pappas, and Dimitris Christodoulou. 2022. Learning to retrieve: Towards a unified framework for information retrieval in pre-trained language models. arXiv preprint arXiv:2203.02144. — [arXiv:2203.02144](https://arxiv.org/abs/2203.02144) [find](https://scholar.google.com/scholar?q=Vasilii+Rubin%2C+Nikolaos+Pappas%2C+and+Dimitris+Christodoulou%2E+2022%2E+Learning+to+retrieve%3A+Towards+a+unified+framework+for+information+retrieval+in+pre%2Dtrained+language+models%2E+arXiv+preprint+arXiv%3A2203%2E)
77. Ankit Singhal, Jayadeva, and Rajat K. De. 2014. On the selection of appropriate distances for gene expression data clustering. BMC Bioinformatics, 15(S2):S2. [find](https://scholar.google.com/scholar?q=Ankit+Singhal%2C+Jayadeva%2C+and+Rajat+K%2E+De%2E+2014%2E+On+the+selection+of+appropriate+distances+for+gene+expression+data+clustering%2E+BMC+Bioinformatics%2C+15%28S2%29%3AS2%2E)
78. Richard Socher, Alex Perelygin, Jean Wu, Jason Chuang, Christopher D Manning, Andrew Y Ng, and Christopher Potts. 2013. [Recursive deep models for semantic compositionality over a sentiment treebank](https://md.research.elamur.ai/free/en/papers/socher-2013-recursive-deep-models-semantic-compositionality/). In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pages 1631…
79. Qwen Team. 2024. Qwen2.5: A family of open-source large language models. [https://github.com/QwenLM/Qwen2.5](https://github.com/QwenLM/Qwen2.5). [↗](https://github.com/QwenLM/Qwen2.5)
80. Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, and Teven Le Scao. 2024. Llama 3: Open and efficient foundation language models. arXiv preprint arXiv:2405.12345. — [arXiv:2405.12345](https://arxiv.org/abs/2405.12345) [find](https://scholar.google.com/scholar?q=Hugo+Touvron%2C+Thibaut+Lavril%2C+Gautier+Izacard%2C+Xavier+Martinet%2C+Marie%2DAnne+Lachaux%2C+Timoth%C3%A9e+Lacroix%2C+and+Teven+Le+Scao%2E+2024%2E+Llama+3%3A+Open+and+efficient+foundation+language+models%2E+arXiv+preprint+ar)
81. Nasib Ullah, Erik Schultheis, Mike Lasby, Yani Ioannou, and Rohit Babbar. 2024. Navigating extremes: Dynamic sparsity in large output spaces. In Advances in Neural Information Processing Systems 37 (NeurIPS 2024). [find](https://scholar.google.com/scholar?q=Nasib+Ullah%2C+Erik+Schultheis%2C+Mike+Lasby%2C+Yani+Ioannou%2C+and+Rohit+Babbar%2E+2024%2E+Navigating+extremes%3A+Dynamic+sparsity+in+large+output+spaces%2E+In+Advances+in+Neural+Information+Processing+Systems+37+%28N)
82. Lean Wang, Lei Li, Damai Dai, Deli Chen, Hao Zhou, Fandong Meng, Jie Zhou, and Xu Sun. 2023. [Label words are anchors: An information flow perspective for understanding in-context learning](https://md.research.elamur.ai/free/en/papers/wang-2023-label-words-anchors-information-flow/). In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 9840–9855.
83. Jason Wei, Yi Tay, Rishi Bommasani, Colin Raffel, Barret Zoph, Sebastian Borgeaud, Dani Yogatama, Maarten Bosma, Denny Zhou, Donald Metzler, Ed H. Chi, Tatsunori Hashimoto, Oriol Vinyals, Percy Liang, Jeff Dean, and William Fedus. 2022a. [Emergent abilities of large language models](https://md.research.elamur.ai/free/en/papers/wei-2022-emergent-abilities-large-language-models/).
84. Trans. Mach. Learn. Res., 2022. [find](https://scholar.google.com/scholar?q=Trans%2E+Mach%2E+Learn%2E+Res%2E%2C+2022%2E)
85. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed H. Chi, Quoc V. Le, and Denny Zhou. 2022b. [Chain-of-thought prompting elicits reasoning in large language models](https://md.research.elamur.ai/free/en/papers/wei-2022-chain-thought-prompting-elicits-reasoning/).
86. Jerry Wei, Le Hou, Andrew Kyle Lampinen, Xiangning Chen, Da Huang, Yi Tay, Xinyun Chen, Yifeng Lu, Denny Zhou, Tengyu Ma, and Quoc V Le. 2023a. Symbol tuning improves in-context learning in language models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pa… [find](https://scholar.google.com/scholar?q=Jerry+Wei%2C+Le+Hou%2C+Andrew+Kyle+Lampinen%2C+Xiangning+Chen%2C+Da+Huang%2C+Yi+Tay%2C+Xinyun+Chen%2C+Yifeng+Lu%2C+Denny+Zhou%2C+Tengyu+Ma%2C+and+Quoc+V+Le%2E+2023a%2E+Symbol+tuning+improves+in%2Dcontext+learning+in+language+m)
87. Jerry Wei, Jason Wei, Yi Tay, Dustin Tran, Albert Webson, Yifeng Lu, Xinyun Chen, Hanxiao Liu, Da Huang, Denny Zhou, and 1 others. 2023b. [Larger language models do in-context learning differently](https://md.research.elamur.ai/free/en/papers/wei-2023-larger-language-models-context-learning/). arXiv preprint arXiv:2303.03846.
88. Zhiyong Wu, Yaoxiang Wang, Jiacheng Ye, and Lingpeng Kong. 2023. Self-adaptive in-context learning: An information compression perspective for in-context example selection and ordering. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)… [find](https://scholar.google.com/scholar?q=Zhiyong+Wu%2C+Yaoxiang+Wang%2C+Jiacheng+Ye%2C+and+Lingpeng+Kong%2E+2023%2E+Self%2Dadaptive+in%2Dcontext+learning%3A+An+information+compression+perspective+for+in%2Dcontext+example+selection+and+ordering%2E+In+Proceedings)
89. Susan Xie, Talia Nisan, Dale Schuurmans, and Richard Sutton. 2021. [An explanation of in-context learning as implicit bayesian inference](https://md.research.elamur.ai/free/en/papers/xie-2021-explanation-context-learning-implicit-bayesian/). arXiv preprint arXiv:2111.02080.
90. Kexin Yin. 2025. Which attention heads matter for in-context learning? arXiv preprint. [find](https://scholar.google.com/scholar?q=Kexin+Yin%2E+2025%2E+Which+attention+heads+matter+for+in%2Dcontext+learning%3F+arXiv+preprint%2E)
91. Zonghao Ying, Aishan Liu, Siyuan Liang, Lei Huang, Jinyang Guo, Wenbo Zhou, Xianglong Liu, and Dacheng Tao. 2026. Safebench: A safety evaluation framework for multimodal large language models. International Journal of Computer Vision, 134(1):18. [find](https://scholar.google.com/scholar?q=Zonghao+Ying%2C+Aishan+Liu%2C+Siyuan+Liang%2C+Lei+Huang%2C+Jinyang+Guo%2C+Wenbo+Zhou%2C+Xianglong+Liu%2C+and+Dacheng+Tao%2E+2026%2E+Safebench%3A+A+safety+evaluation+framework+for+multimodal+large+language+models%2E+Interna)
92. Shuyang Yu, Runxue Bao, Parminder Bhatia, Taha Kass-Hout, Jiayu Zhou, and Cao Xiao. 2025. Dynamic uncertainty ranking: Enhancing retrieval-augmented in-context learning for long-tail knowledge in llms. In Proceedings of the 2025 Conference of the North American Chapter of the Association for Computa… [find](https://scholar.google.com/scholar?q=Shuyang+Yu%2C+Runxue+Bao%2C+Parminder+Bhatia%2C+Taha+Kass%2DHout%2C+Jiayu+Zhou%2C+and+Cao+Xiao%2E+2025%2E+Dynamic+uncertainty+ranking%3A+Enhancing+retrieval%2Daugmented+in%2Dcontext+learning+for+long%2Dtail+knowledge+in+llms)
93. Jinghua Zhang, Li Liu, Olli Silvén, Matti Pietikäinen, and Dewen Hu. 2025. Few-shot class-incremental learning for classification and object detection: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence. [find](https://scholar.google.com/scholar?q=Jinghua+Zhang%2C+Li+Liu%2C+Olli+Silv%C3%A9n%2C+Matti+Pietik%C3%A4inen%2C+and+Dewen+Hu%2E+2025%2E+Few%2Dshot+class%2Dincremental+learning+for+classification+and+object+detection%3A+A+survey%2E+IEEE+Transactions+on+Pattern+Analysis+)
94. Overview of the Appendix This appendix includes our supplementary materials as follows: • A review of related work in Section A. [find](https://scholar.google.com/scholar?q=Overview+of+the+Appendix+This+appendix+includes+our+supplementary+materials+as+follows%3A+%E2%80%A2+A+review+of+related+work+in+Section+A%2E)
95. Yucheng Zhou, Xiang Li, Qianning Wang, and Jianbing Shen. 2024. Visual in-context learning for large vision-language models. arXiv preprint arXiv:2402.11574. [find](https://scholar.google.com/scholar?q=Yucheng+Zhou%2C+Xiang+Li%2C+Qianning+Wang%2C+and+Jianbing+Shen%2E+2024%2E+Visual+in%2Dcontext+learning+for+large+vision%2Dlanguage+models%2E+arXiv+preprint+arXiv%3A2402%2E11574%2E)
96. Details of the model architecture and training setup in Section B. [find](https://scholar.google.com/scholar?q=Details+of+the+model+architecture+and+training+setup+in+Section+B%2E)
97. Yucheng Zhou, Tao Shen, Xiubo Geng, Chongyang Tao, Can Xu, Guodong Long, Binxing Jiao, and Daxin Jiang. 2023. Towards robust ranker for text retrieval. In Findings of the Association for Computational Linguistics: ACL 2023, Toronto, Canada, July 9-14, 2023, pages 5387–5401. Association for Computati… [find](https://scholar.google.com/scholar?q=Yucheng+Zhou%2C+Tao+Shen%2C+Xiubo+Geng%2C+Chongyang+Tao%2C+Can+Xu%2C+Guodong+Long%2C+Binxing+Jiao%2C+and+Daxin+Jiang%2E+2023%2E+Towards+robust+ranker+for+text+retrieval%2E+In+Findings+of+the+Association+for+Computational)
98. Results of various pre-trained models and similarity computation in Section C. • Descriptions of baseline methods in Section D. • Analysis under different missing-label proportions in Section E. [find](https://scholar.google.com/scholar?q=Results+of+various+pre%2Dtrained+models+and+similarity+computation+in+Section+C%2E+%E2%80%A2+Descriptions+of+baseline+methods+in+Section+D%2E+%E2%80%A2+Analysis+under+different+missing%2Dlabel+proportions+in+Section+E%2E)
99. Mingli Zhu, Siyuan Liang, and Baoyuan Wu. 2024. Breaking the false sense of security in backdoor defense through re-activation attack. Advances in Neural Information Processing Systems, 37:114928– 114964. [find](https://scholar.google.com/scholar?q=Mingli+Zhu%2C+Siyuan+Liang%2C+and+Baoyuan+Wu%2E+2024%2E+Breaking+the+false+sense+of+security+in+backdoor+defense+through+re%2Dactivation+attack%2E+Advances+in+Neural+Information+Processing+Systems%2C+37%3A114928%E2%80%93+114)
100. Experiments on semi-supervised IICL in Section F. • Experiments on standard ICL in Section G. • Experiments on prompt learning in Section H. • More detailed descriptions of the evaluation metrics in Section I. • Formal definitions of the tasks in Section J. • More details about the dataset in Sectio… [find](https://scholar.google.com/scholar?q=Experiments+on+semi%2Dsupervised+IICL+in+Section+F%2E+%E2%80%A2+Experiments+on+standard+ICL+in+Section+G%2E+%E2%80%A2+Experiments+on+prompt+learning+in+Section+H%2E+%E2%80%A2+More+detailed+descriptions+of+the+evaluation+metrics+in+S)

*Updated 1 November 2026*