---
title: "Uncertainty-Aware Contrastive Sentence Embedding With Local"
description: "The paper tackles a frozen pre-trained language model whose sentence vectors are poorly tuned for text classification. 44 references."
authors: ["Han Liu", "Jiaqing Zhan", "Zhichao Chen", "Qin Zhang"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.1927/"
doi: "10.18653/v1/2026.findings-acl.1927"
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/liu-2026-uncertainty-aware-contrastive-sentence-embedding/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/liu-2026-uncertainty-aware-contrastive-sentence-embedding/)

[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/18/) / Uncertainty-Aware Contrastive Sentence Embedding With Local Context Representation for Text Classification

# Uncertainty-Aware Contrastive Sentence Embedding With Local Context Representation for Text Classification

**Authors:** [Han Liu](https://md.research.elamur.ai/free/en/authors/han-liu/), Jiaqing Zhan, Zhichao Chen and Qin Zhang · **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.1927/) · [PDF](https://aclanthology.org/2026.findings-acl.1927.pdf) · [DOI 10.18653/v1/2026.findings-acl.1927](https://doi.org/10.18653/v1/2026.findings-acl.1927) · [OpenAlex](https://openalex.org/W7166864989)

**Citations:** 1 citations (OpenAlex, 2026-10-14)

## Summary
The paper tackles a frozen pre-trained language model whose sentence vectors are poorly tuned for text classification. Standard pooling, such as the EOS or CLS token, captures global meaning but misses dependencies between nearby tokens. It also handles every sentence as equally clear, including ambiguous ones like a neutral tweet that contains negative words. The authors keep the backbone (Qwen3-Embedding) frozen and train a lightweight head on its last-layer hidden states. The head is a TextCNN-style 1D convolutional network with several kernel sizes and max-pooling, which extracts local context at multiple granularities. Two output branches predict a mean vector and an uncertainty (variance), and the reparameterization trick turns these into a stochastic sentence embedding. A label-wise contrastive loss pulls same-class samples together and pushes different classes apart. The authors report higher accuracy than state-of-the-art embedding baselines on public datasets and show that smaller embedding models can beat larger ones. The provided excerpt omits the exact accuracy tables. The extra compute is small, and the uncertainty scores help flag low-confidence inputs.

## Key points
- **Components:** an uncertainty module (UCL) based on data uncertainty learning in the style of Chang et al. (2020), plus label-wise contrastive learning (LCL). Only the downstream modules are trained, and the backbone stays frozen. Code is available on GitHub (stickDONTdip/Uncertainty-Aware-Contrastive-Sentence-Embedding).
- **Data:** the case studies use TweetSentimentExtraction, and the uncertainty analysis uses the IMDB test set. In that analysis, test samples are binned into Easy, Semi-hard and Hard groups using uncertainty thresholds of 0.8 and 1.0. With UCL, errors concentrate in the Hard group, and Accuracy-Rejection Curves show accuracy rising as uncertain samples are rejected.
- **Representation space:** t-SNE plots show that LCL widens the margins between classes. The combined method yields compact, well-separated clusters in both the EOS-based and TextCNN-based setups.
- **Efficiency:** parameters grow from 595.9M to 614.7M (+3.16%). Latency rises from 2.72 to 2.76 ms (+0.037 ms, about 1.36%), and throughput drops from 367.0 to 362.1 samples/s.
- **Limitations:** the method has been tested on English only, and languages like Chinese or Japanese may need tokenization changes. The objective is built for classification and is not suited to generation.

*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

- [Shenzhen University](https://md.research.elamur.ai/free/en/universities/shenzhen-university/) — University, Shenzhen, China · 16 works · 95 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

## Cite

Cite as: Han Liu, Jiaqing Zhan, Zhichao Chen and Qin Zhang. 2026. Uncertainty-Aware Contrastive Sentence Embedding With Local Context Representation for Text 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{liu2026uncertainty,
  title = {{Uncertainty-Aware Contrastive Sentence Embedding With Local Context Representation for Text Classification}},
  author = {Han Liu, Jiaqing Zhan, Zhichao Chen and Qin Zhang},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.1927},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.1927}
}
```

- [← previous Uncertainty Quantification for Evaluating Gender Bias in Machine Translation](https://md.research.elamur.ai/free/en/papers/staliunaite-2026-uncertainty-quantification-evaluating-gender-bias/)
- [next → Uncovering Intervention Opportunities for Suicide Prevention with Language Model Assistants](https://md.research.elamur.ai/free/en/papers/ranjit-2026-uncovering-intervention-opportunities-suicide-prevention/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/18/)

## References

44 references, 17 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Moloud Abdar, Farhad Pourpanah, Sadiq Hussain, Dana Rezazadegan, Li Liu, Mohammad Ghavamzadeh, Paul Fieguth, Xiaochun Cao, Abbas Khosravi, U. Rajendra Acharya, Vladimir Makarenkov, and Saeid Nahavandi. 2021. A review of uncertainty quantification in deep learning: Techniques, applications and challe… [find](https://scholar.google.com/scholar?q=Moloud+Abdar%2C+Farhad+Pourpanah%2C+Sadiq+Hussain%2C+Dana+Rezazadegan%2C+Li+Liu%2C+Mohammad+Ghavamzadeh%2C+Paul+Fieguth%2C+Xiaochun+Cao%2C+Abbas+Khosravi%2C+U%2E+Rajendra+Acharya%2C+Vladimir+Makarenkov%2C+and+Saeid+Nahavandi)
2. Parishad BehnamGhader, Vaibhav Adlakha, Marius Mosbach, Dzmitry Bahdanau, Nicolas Chapados, and Siva Reddy. 2024. [LLM2Vec: Large language models are secretly powerful text encoders](https://md.research.elamur.ai/free/en/papers/behnamghader-2024-llm2vec-large-language-models-secretly/). arXiv preprint arXiv:2404.05961.
3. Jie Chang, Zhonghao Lan, Changmao Cheng, and Yichen Wei. 2020. Data uncertainty learning in face recognition. In Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 5710–5719, Online. IEEE. [find](https://scholar.google.com/scholar?q=Jie+Chang%2C+Zhonghao+Lan%2C+Changmao+Cheng%2C+and+Yichen+Wei%2E+2020%2E+Data+uncertainty+learning+in+face+recognition%2E+In+Proceedings+of+IEEE%2FCVF+Conference+on+Computer+Vision+and+Pattern+Recognition+%28CVPR%29%2C+p)
4. Chanyeol Choi, Junseong Kim, Seolhwa Lee, Jihoon Kwon, Sangmo Gu, Yejin Kim, Minkyung Cho, and Jy-yong Sohn. 2024. Linq-embed-mistral technical report. arXiv preprint arXiv:2412.03223. — [arXiv:2412.03223](https://arxiv.org/abs/2412.03223) [find](https://scholar.google.com/scholar?q=Chanyeol+Choi%2C+Junseong+Kim%2C+Seolhwa+Lee%2C+Jihoon+Kwon%2C+Sangmo+Gu%2C+Yejin+Kim%2C+Minkyung+Cho%2C+and+Jy%2Dyong+Sohn%2E+2024%2E+Linq%2Dembed%2Dmistral+technical+report%2E+arXiv+preprint+arXiv%3A2412%2E03223%2E+%E2%80%94+%5BarXiv%3A2412%2E0)
5. Jooyoung Choi, Hyun Kim, Hansol Jang, Changwook Jun, Kyunghoon Bae, Hyewon Choi, Stanley Jungkyu Choi, Honglak Lee, and Chulmin Yun. 2025. Lgai-embedding-preview technical report. CoRR. [find](https://scholar.google.com/scholar?q=Jooyoung+Choi%2C+Hyun+Kim%2C+Hansol+Jang%2C+Changwook+Jun%2C+Kyunghoon+Bae%2C+Hyewon+Choi%2C+Stanley+Jungkyu+Choi%2C+Honglak+Lee%2C+and+Chulmin+Yun%2E+2025%2E+Lgai%2Dembedding%2Dpreview+technical+report%2E+CoRR%2E)
6. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. [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 Annual Conference of the North American Chapter of the Association for Computational Linguistics, pages 4171–4186, New Orleans,…
7. Kenneth Enevoldsen, Isaac Chung, Imene Kerboua, Márton Kardos, Ashwin Mathur, David Stap, Jay Gala, Wissam Siblini, Dominik Krzeminski, Genta Indra Winata, and 1 others. 2025. [MMTEB: Massive multilingual text embedding benchmark](https://md.research.elamur.ai/free/en/papers/enevoldsen-2025-mmteb-massive-multilingual-text-embedding/). In International Conference on Learning Representations.
8. Nicholas Frosst, Nicolas Papernot, and Geoffrey Hinton. 2019. Analyzing and improving representations with the soft nearest neighbor loss. In International Conference on Machine Learning, pages 2012–2020. PMLR. [find](https://scholar.google.com/scholar?q=Nicholas+Frosst%2C+Nicolas+Papernot%2C+and+Geoffrey+Hinton%2E+2019%2E+Analyzing+and+improving+representations+with+the+soft+nearest+neighbor+loss%2E+In+International+Conference+on+Machine+Learning%2C+pages+2012%E2%80%932)
9. 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 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021, pages 6894–6910, Punta Cana, Dominican Republic. Association for Computational Linguistics (ACL).
10. Anchun Gui and Han Xiao. 2024. Multi-level multilingual semantic alignment for zero-shot cross-lingual transfer learning. Neural Networks, 173:106217. [find](https://scholar.google.com/scholar?q=Anchun+Gui+and+Han+Xiao%2E+2024%2E+Multi%2Dlevel+multilingual+semantic+alignment+for+zero%2Dshot+cross%2Dlingual+transfer+learning%2E+Neural+Networks%2C+173%3A106217%2E)
11. Dong Guo, Faming Wu, Feida Zhu, Fuxing Leng, Guang Shi, Haobin Chen, Haoqi Fan, Jian Wang, Jianyu Jiang, Jiawei Wang, and 1 others. 2025. Seed1. 5-vl technical report. arXiv preprint arXiv:2505.07062. — [Seed1.5-VL Technical Report](https://md.research.elamur.ai/free/en/papers/guo-2025-seed1-5-vl-technical/)
12. Saumya Gupta, Yikai Zhang, Xiaoling Hu, Prateek Prasanna, and Chao Chen. 2024. Topology-aware uncertainty for image segmentation. Advances in Neural Information Processing Systems, 36. [find](https://scholar.google.com/scholar?q=Saumya+Gupta%2C+Yikai+Zhang%2C+Xiaoling+Hu%2C+Prateek+Prasanna%2C+and+Chao+Chen%2E+2024%2E+Topology%2Daware+uncertainty+for+image+segmentation%2E+Advances+in+Neural+Information+Processing+Systems%2C+36%2E)
13. Chao Huang, Yushu Shi, Bob Zhang, and Ke Lyu. 2024. Uncertainty-aware prototypical learning for anomaly detection in medical images. Neural Networks, 175:106284. [find](https://scholar.google.com/scholar?q=Chao+Huang%2C+Yushu+Shi%2C+Bob+Zhang%2C+and+Ke+Lyu%2E+2024%2E+Uncertainty%2Daware+prototypical+learning+for+anomaly+detection+in+medical+images%2E+Neural+Networks%2C+175%3A106284%2E)
14. Prannay Khosla, Piotr Teterwak, Chen Wang, Aaron Sarna, Yonglong Tian, Phillip Isola, Aaron Maschinot, Ce Liu, and Dilip Krishnan. 2020. Supervised contrastive learning. Advances in Neural Information Processing Systems, 33:18661–18673. [find](https://scholar.google.com/scholar?q=Prannay+Khosla%2C+Piotr+Teterwak%2C+Chen+Wang%2C+Aaron+Sarna%2C+Yonglong+Tian%2C+Phillip+Isola%2C+Aaron+Maschinot%2C+Ce+Liu%2C+and+Dilip+Krishnan%2E+2020%2E+Supervised+contrastive+learning%2E+Advances+in+Neural+Information)
15. Diederik P. Kingma and Max Welling. 2014. Autoencoding variational bayes. In 2nd International Conference on Learning Representations (ICLR), page 14, Banff, Canada. [find](https://scholar.google.com/scholar?q=Diederik+P%2E+Kingma+and+Max+Welling%2E+2014%2E+Autoencoding+variational+bayes%2E+In+2nd+International+Conference+on+Learning+Representations+%28ICLR%29%2C+page+14%2C+Banff%2C+Canada%2E)
16. Puneet Kumar and Balasubramanian Raman. 2022. A bert based dual-channel explainable text emotion recognition system. Neural Networks, 150:392–407. [find](https://scholar.google.com/scholar?q=Puneet+Kumar+and+Balasubramanian+Raman%2E+2022%2E+A+bert+based+dual%2Dchannel+explainable+text+emotion+recognition+system%2E+Neural+Networks%2C+150%3A392%E2%80%93407%2E)
17. Chankyu Lee, Rajarshi Roy, Mengyao Xu, Jonathan Raiman, Mohammad Shoeybi, Bryan Catanzaro, and Wei Ping. 2025a. [NV-Embed: Improved techniques for training LLMs as generalist embedding models](https://md.research.elamur.ai/free/en/papers/lee-2024-nv-embed-improved-techniques-training/). In The Thirteenth International Conference on Learning Representations.
18. Jinhyuk Lee, Feiyang Chen, Sahil Dua, Daniel Cer, Madhuri Shanbhogue, Iftekhar Naim, Gustavo Hernández Ábrego, Zhe Li, Kaifeng Chen, Henrique Schechter Vera, and 1 others. 2025b. [Gemini embedding: Generalizable embeddings from gemini](https://md.research.elamur.ai/free/en/papers/lee-2025-gemini-embedding-generalizable-embeddings-gemini/). arXiv preprint arXiv:2503.07891.
19. Jianmo Ni, Gustavo Hernandez Abrego, Noah Constant, Ji Ma, Keith Hall, Daniel Cer, and Yinfei Yang. 2022. [Sentence-T5: Scalable sentence encoders from pre-trained text-to-text models](https://md.research.elamur.ai/free/en/papers/ni-2021-sentence-t5-scalable-sentence-encoders/). In Findings of the Association for Computational Linguistics: ACL 2022, pages 1864–1874, Dublin, Ireland. Associatio…
20. Wanhua Li, Xiaoke Huang, Jiwen Lu, Jianjiang Feng, and Jie Zhou. 2021. Learning probabilistic ordinal embeddings for uncertainty-aware regression. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 13896– 13905, Nashville, USA. IEEE. [find](https://scholar.google.com/scholar?q=Wanhua+Li%2C+Xiaoke+Huang%2C+Jiwen+Lu%2C+Jianjiang+Feng%2C+and+Jie+Zhou%2E+2021%2E+Learning+probabilistic+ordinal+embeddings+for+uncertainty%2Daware+regression%2E+In+Proceedings+of+the+IEEE%2FCVF+Conference+on+Computer)
21. Zhijie Nie, Zhangchi Feng, Mingxin Li, Cunwang Zhang, Yanzhao Zhang, Dingkun Long, and Richong Zhang. 2024. When text embedding meets large language model: a comprehensive survey. arXiv preprint arXiv:2412.09165. — [arXiv:2412.09165](https://arxiv.org/abs/2412.09165) [find](https://scholar.google.com/scholar?q=Zhijie+Nie%2C+Zhangchi+Feng%2C+Mingxin+Li%2C+Cunwang+Zhang%2C+Yanzhao+Zhang%2C+Dingkun+Long%2C+and+Richong+Zhang%2E+2024%2E+When+text+embedding+meets+large+language+model%3A+a+comprehensive+survey%2E+arXiv+preprint+arXiv)
22. Zehan Li, Xin Zhang, Yanzhao Zhang, Dingkun Long, Pengjun Xie, and Meishan Zhang. 2023. [Towards general text embeddings with multi-stage contrastive learning](https://md.research.elamur.ai/free/en/papers/li-2023-towards-general-text-embeddings-multi/). arXiv preprint arXiv:2308.03281.
23. Jeffrey Pennington, Richard Socher, and Christopher Manning. 2014. [GloVe: Global vectors for word representation](https://md.research.elamur.ai/free/en/papers/pennington-2014-glove-global-vectors-word-representation/). In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, pages 1532–1543, Doha, Qatar. Association for Computational Linguistics.
24. Tao Liu, Jiahao Liu, Dong Li, and Shan Tan. 2025a. Bayesian deep-learning structured illumination microscopy enables reliable super-resolution imaging with uncertainty quantification. Nature Communications, 16(1):5027. [find](https://scholar.google.com/scholar?q=Tao+Liu%2C+Jiahao+Liu%2C+Dong+Li%2C+and+Shan+Tan%2E+2025a%2E+Bayesian+deep%2Dlearning+structured+illumination+microscopy+enables+reliable+super%2Dresolution+imaging+with+uncertainty+quantification%2E+Nature+Communica)
25. Xiaolu Liu, Ruizi Yang, Song Wang, Wentong Li, Junbo Chen, and Jianke Zhu. 2025b. Uncertainty-instructed structure injection for generalizable hd map construction. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 22359–22368. [find](https://scholar.google.com/scholar?q=Xiaolu+Liu%2C+Ruizi+Yang%2C+Song+Wang%2C+Wentong+Li%2C+Junbo+Chen%2C+and+Jianke+Zhu%2E+2025b%2E+Uncertainty%2Dinstructed+structure+injection+for+generalizable+hd+map+construction%2E+In+Proceedings+of+the+IEEE%2FCVF+Confe)
26. 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.
27. Alec Radford, Karthik Narasimhan, Tim Salimans, and Ilya Sutskever. 2018. Improving language understanding by generative pre-training. Technical Report 4, OpenAI, San Francisco, CA, USA. [find](https://scholar.google.com/scholar?q=Alec+Radford%2C+Karthik+Narasimhan%2C+Tim+Salimans%2C+and+Ilya+Sutskever%2E+2018%2E+Improving+language+understanding+by+generative+pre%2Dtraining%2E+Technical+Report+4%2C+OpenAI%2C+San+Francisco%2C+CA%2C+USA%2E)
28. Nils Reimers and Iryna Gurevych. 2019. [Sentence-BERT: Sentence embeddings using siamese bert-networks](https://md.research.elamur.ai/free/en/papers/reimers-2019-sentence-bert-sentence-embeddings-siamese/). In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 3982–3992,…
29. Haojing Shen, Sihong Chen, Ran Wang, and Xizhao Wang. 2023a. Adversarial learning with cost-sensitive classes. IEEE Transactions on Cybernetics, 53(8):4855–4866. [find](https://scholar.google.com/scholar?q=Haojing+Shen%2C+Sihong+Chen%2C+Ran+Wang%2C+and+Xizhao+Wang%2E+2023a%2E+Adversarial+learning+with+cost%2Dsensitive+classes%2E+IEEE+Transactions+on+Cybernetics%2C+53%288%29%3A4855%E2%80%934866%2E)
30. Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. [Distributed representations of words and phrases and their compositionality](https://md.research.elamur.ai/free/en/papers/mikolov-2013-distributed-representations-words-phrases-their/). In Proceedings of the 27th Conference on Neural Information Processing Systems, pages 3111–3119, Lake Tahoe, USA. Curran Associates.
31. Lingfeng Shen, Haiyun Jiang, Lemao Liu, and Shuming Shi. 2023b. Sen2Pro: A probabilistic perspective to sentence embedding from pre-trained language model. In Proceedings of the 8th Workshop on Representation Learning for NLP (RepL4NLP 2023), pages 315–333. [find](https://scholar.google.com/scholar?q=Lingfeng+Shen%2C+Haiyun+Jiang%2C+Lemao+Liu%2C+and+Shuming+Shi%2E+2023b%2E+Sen2Pro%3A+A+probabilistic+perspective+to+sentence+embedding+from+pre%2Dtrained+language+model%2E+In+Proceedings+of+the+8th+Workshop+on+Repres)
32. Niklas Muennighoff, Hongjin Su, Liang Wang, Nan Yang, Furu Wei, Tao Yu, Amanpreet Singh, and Douwe Kiela. 2025. [Generative representational instruction tuning](https://md.research.elamur.ai/free/en/papers/muennighoff-2024-generative-representational-instruction-tuning/). In The Thirteenth International Conference on Learning Representations.
33. Dianmo Sheng, Dongdong Chen, Zhentao Tan, Qiankun Liu, Qi Chu, Tao Gong, Bin Liu, Jing Han, Wenbin Tu, Shengwei Xu, and Nenghai Yu. 2025. Unicl-sam: Uncertainty-driven in-context segmentation with part prototype discovery. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Reco… [find](https://scholar.google.com/scholar?q=Dianmo+Sheng%2C+Dongdong+Chen%2C+Zhentao+Tan%2C+Qiankun+Liu%2C+Qi+Chu%2C+Tao+Gong%2C+Bin+Liu%2C+Jing+Han%2C+Wenbin+Tu%2C+Shengwei+Xu%2C+and+Nenghai+Yu%2E+2025%2E+Unicl%2Dsam%3A+Uncertainty%2Ddriven+in%2Dcontext+segmentation+with+par)
34. Niklas Muennighoff, Nouamane Tazi, Loic Magne, and Nils Reimers. 2023. [MTEB: Massive text embedding benchmark](https://md.research.elamur.ai/free/en/papers/muennighoff-2022-mteb-massive-text-embedding-benchmark/). In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics. Association for Computational Linguistics.
35. Malik Sajjad Ahmed Nadeem, Jean-Daniel Zucker, and Blaise Hanczar. 2009. Accuracy-rejection curves (ARCs) for comparing classification methods with a reject option. In Machine Learning in Systems Biology, pages 65–81. PMLR. [find](https://scholar.google.com/scholar?q=Malik+Sajjad+Ahmed+Nadeem%2C+Jean%2DDaniel+Zucker%2C+and+Blaise+Hanczar%2E+2009%2E+Accuracy%2Drejection+curves+%28ARCs%29+for+comparing+classification+methods+with+a+reject+option%2E+In+Machine+Learning+in+Systems+Biol)
36. Jacob Mitchell Springer, Suhas Kotha, Daniel Fried, Graham Neubig, and Aditi Raghunathan. 2024. Repetition improves language model embeddings. arXiv preprint arXiv:2402.15449. [find](https://scholar.google.com/scholar?q=Jacob+Mitchell+Springer%2C+Suhas+Kotha%2C+Daniel+Fried%2C+Graham+Neubig%2C+and+Aditi+Raghunathan%2E+2024%2E+Repetition+improves+language+model+embeddings%2E+arXiv+preprint+arXiv%3A2402%2E15449%2E)
37. Henrique Schechter Vera, Sahil Dua, Biao Zhang, Daniel Salz, Ryan Mullins, Sindhu Raghuram Panyam, Sara Smoot, Iftekhar Naim, Joe Zou, Feiyang Chen, and 1 others. 2025. Embeddinggemma: Powerful and lightweight text representations. arXiv preprint arXiv:2509.20354. — [arXiv:2509.20354](https://arxiv.org/abs/2509.20354) [find](https://scholar.google.com/scholar?q=Henrique+Schechter+Vera%2C+Sahil+Dua%2C+Biao+Zhang%2C+Daniel+Salz%2C+Ryan+Mullins%2C+Sindhu+Raghuram+Panyam%2C+Sara+Smoot%2C+Iftekhar+Naim%2C+Joe+Zou%2C+Feiyang+Chen%2C+and+1+others%2E+2025%2E+Embeddinggemma%3A+Powerful+and+li)
38. Ranwan Wu, Tian-Zhu Xiang, Guo-Sen Xie, Rongrong Gao, Xiangbo Shu, Fang Zhao, and Ling Shao. 2025. Uncertainty-aware transformer for referring camouflaged object detection. IEEE Transactions on Image Processing, 34:5341–5354. [find](https://scholar.google.com/scholar?q=Ranwan+Wu%2C+Tian%2DZhu+Xiang%2C+Guo%2DSen+Xie%2C+Rongrong+Gao%2C+Xiangbo+Shu%2C+Fang+Zhao%2C+and+Ling+Shao%2E+2025%2E+Uncertainty%2Daware+transformer+for+referring+camouflaged+object+detection%2E+IEEE+Transactions+on+Image+)
39. Shohei Yoda, Hayato Tsukagoshi, Ryohei Sasano, and Koichi Takeda. 2024. Sentence representations via gaussian embedding. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers), pages 418–425. [find](https://scholar.google.com/scholar?q=Shohei+Yoda%2C+Hayato+Tsukagoshi%2C+Ryohei+Sasano%2C+and+Koichi+Takeda%2E+2024%2E+Sentence+representations+via+gaussian+embedding%2E+In+Proceedings+of+the+18th+Conference+of+the+European+Chapter+of+the+Associatio)
40. Wenqiao Zhang and Zheqi Lv. 2024. Revisiting the domain shift and sample uncertainty in multi-source active domain transfer. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 16751–16761. [find](https://scholar.google.com/scholar?q=Wenqiao+Zhang+and+Zheqi+Lv%2E+2024%2E+Revisiting+the+domain+shift+and+sample+uncertainty+in+multi%2Dsource+active+domain+transfer%2E+In+Proceedings+of+the+IEEE%2FCVF+Conference+on+Computer+Vision+and+Pattern+Re)
41. Xin Zhang, Yanzhao Zhang, Dingkun Long, Wen Xie, Ziqi Dai, Jialong Tang, Huan Lin, Baosong Yang, Pengjun Xie, Fei Huang, Meishan Zhang, Wenjie Li, and Min Zhang. 2024. [mGTE: Generalized long-context text representation and reranking models for multilingual text retrieval](https://md.research.elamur.ai/free/en/papers/zhang-2024-mgte-generalized-long-context-text/). In Proceedings of the 2024…
42. Yanzhao Zhang, Mingxin Li, Dingkun Long, Xin Zhang, Huan Lin, Baosong Yang, Pengjun Xie, An Yang, Dayiheng Liu, Junyang Lin, and 1 others. 2025a. [Qwen3 embedding: Advancing text embedding and reranking through foundation models](https://md.research.elamur.ai/free/en/papers/zhang-2025-qwen3-embedding-advancing-text/). arXiv preprint arXiv:2506.05176.
43. Ziyin Zhang, Zihan Liao, Hang Yu, Peng Di, and Rui Wang. 2025b. F2LLM technical report: Matching SOTA embedding performance with 6 million open-source data. arXiv preprint arXiv:2510.02294. — [arXiv:2510.02294](https://arxiv.org/abs/2510.02294) [find](https://scholar.google.com/scholar?q=Ziyin+Zhang%2C+Zihan+Liao%2C+Hang+Yu%2C+Peng+Di%2C+and+Rui+Wang%2E+2025b%2E+F2LLM+technical+report%3A+Matching+SOTA+embedding+performance+with+6+million+open%2Dsource+data%2E+arXiv+preprint+arXiv%3A2510%2E02294%2E+%E2%80%94+%5BarXiv%3A2)
44. Xinping Zhao, Xinshuo Hu, Zifei Shan, Shouzheng Huang, Yao Zhou, Xin Zhang, Zetian Sun, Zhenyu Liu, Dongfang Li, Xinyuan Wei, and 1 others. 2025. KaLm-Embedding-V2: Superior training techniques and data inspire a versatile embedding model. arXiv preprint arXiv:2506.20923. — [arXiv:2506.20923](https://arxiv.org/abs/2506.20923) [find](https://scholar.google.com/scholar?q=Xinping+Zhao%2C+Xinshuo+Hu%2C+Zifei+Shan%2C+Shouzheng+Huang%2C+Yao+Zhou%2C+Xin+Zhang%2C+Zetian+Sun%2C+Zhenyu+Liu%2C+Dongfang+Li%2C+Xinyuan+Wei%2C+and+1+others%2E+2025%2E+KaLm%2DEmbedding%2DV2%3A+Superior+training+techniques+and+da)

*Updated 31 October 2026*