---
title: "NiuTrans.LMT — paper by Luo et al. (2026) — summary and ideas"
description: "The paper addresses how to adapt LLMs for translation across many languages without quality collapsing in some directions. 50 references."
authors: ["Yingfeng Luo", "Ziqiang Xu", "Yuxuan Ouyang", "MuRun Yang", "DingYang Lin", "Kaiyan Chang", "Tong Zheng", "Bei Li", "Peinan Feng", "Quan Du", "Tong Xiao", "JingBo Zhu"]
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.1153/"
doi: "10.18653/v1/2026.acl-long.1153"
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/luo-2026-niutrans-lmt-inclusive-scalable-multilingual/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/luo-2026-niutrans-lmt-inclusive-scalable-multilingual/)

[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/43/) / NiuTrans.LMT: Toward Inclusive and Scalable Multilingual Machine Translation with LLMs

# NiuTrans.LMT: Toward Inclusive and Scalable Multilingual Machine Translation with LLMs

**Authors:** [Yingfeng Luo](https://md.research.elamur.ai/free/en/authors/yingfeng-luo/), Ziqiang Xu, [Yuxuan Ouyang](https://md.research.elamur.ai/free/en/authors/yuxuan-ouyang/), [MuRun Yang](https://md.research.elamur.ai/free/en/authors/murun-yang/), [DingYang Lin](https://md.research.elamur.ai/free/en/authors/dingyang-lin/), [Kaiyan Chang](https://md.research.elamur.ai/free/en/authors/kaiyan-chang/), Tong Zheng, [Bei Li](https://md.research.elamur.ai/free/en/authors/bei-li/), Peinan Feng, [Quan Du](https://md.research.elamur.ai/free/en/authors/quan-du/), [Tong Xiao](https://md.research.elamur.ai/free/en/authors/tong-xiao/) and [JingBo Zhu](https://md.research.elamur.ai/free/en/authors/jingbo-zhu/) · **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.1153/) · [PDF](https://aclanthology.org/2026.acl-long.1153.pdf) · [DOI 10.18653/v1/2026.acl-long.1153](https://doi.org/10.18653/v1/2026.acl-long.1153) · [OpenAlex](https://openalex.org/W7166838888)

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

## Summary
The paper addresses how to adapt LLMs for translation across many languages without quality collapsing in some directions. The authors find that standard multilingual SFT can backfire when multi-way parallel corpora are used symmetrically around a pivot such as English or Chinese. Translation from the pivot improves, but translation back into the pivot degrades into fluent yet unfaithful output. They name this Directional Degeneration. They trace it to a single pivot sentence being the target for dozens of source languages, which lets the model memorize frequent targets instead of reading the source. Their fix, Strategic Downsampling (SD), keeps all pivot→X data but only a small share of reverse pairs. They also propose Parallel Multilingual Prompting (PMP), which adds an auxiliary parallel sentence to the instruction during training and optionally at inference. The resulting models, NiuTrans.LMT, are built on Qwen3 through CPT, SFT and GRPO. They cover 60 languages and 234 directions, centered on both Chinese and English. This makes them a strong open baseline beyond English-only translation.

## Key points
- **Models:** four sizes (0.6B, 1.7B, 4B, 8B) built on Qwen3 base models.
  - Training pipeline: about 90B tokens of continued pre-training, then SFT with SD and PMP, then GRPO that reuses the SFT pairs.
- **SFT data:** roughly 567K human-quality pairs, with 3K–20K examples per direction across 117 En/Zh-centric directions.
  - Sources: Flores-200 devset, NTREX-128, SMol, and WMT14–23 / IWSLT17–24 test sets.
- **Downsampling results:** varying the retained share of reverse data traces an inverted-V curve in COMET.
  - Reverse-direction quality peaks at about 5% retention and falls sharply toward full symmetric reuse.
  - The effect appears across Qwen3 sizes, Llama-3.1-8B and Gemma-2-9B.
  - It grows stronger as the number of languages increases from 10 to 50.
- **PMP:** helps zero-shot cross-lingual transfer.
  - At test time it can use the model's own auxiliary translations to improve X→En/Zh output.
- **Headline result:** LMT-60-4B matches or beats much larger systems, namely X-ALMA-13B, Aya-101-13B and NLLB-54B, on the directions they share.
  - The models are publicly released (NiuTrans/LMT).

*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

- [Northeastern University](https://md.research.elamur.ai/free/en/universities/northeastern-university-cn/) — University, Shenyang, China · 53 works · 2,205 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

🧭 Topics (2): [🔁 Machine translation](https://md.research.elamur.ai/free/en/topics/machine-translation/) · 1,105 works · [🌍 Multilingual & cross-lingual NLP](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/) · 882 works

## Cite

Cite as: Yingfeng Luo, Ziqiang Xu, Yuxuan Ouyang, MuRun Yang, DingYang Lin, Kaiyan Chang, Tong Zheng, Bei Li, Peinan Feng, Quan Du, Tong Xiao and JingBo Zhu. 2026. NiuTrans.LMT: Toward Inclusive and Scalable Multilingual Machine Translation with LLMs. 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{luo2026niutrans,
  title = {{NiuTrans.LMT: Toward Inclusive and Scalable Multilingual Machine Translation with LLMs}},
  author = {Yingfeng Luo, Ziqiang Xu, Yuxuan Ouyang, MuRun Yang, DingYang Lin, Kaiyan Chang, Tong Zheng, Bei Li, Peinan Feng, Quan Du, Tong Xiao and JingBo Zhu},
  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.1153},
  url = {https://doi.org/10.18653/v1/2026.acl-long.1153}
}
```

- [← previous NITI: Neural Plan Concretization for Incremental Execution, Bridging and Trigger Inference from Underspecified Human Policies](https://md.research.elamur.ai/free/en/papers/banerjee-2026-niti-neural-plan-concretization-incremental/)
- [next → NJUSTKMG at SemEval 2026 Task 10 PsyCoMark–-Subtask 2:Conspiracy Detection](https://md.research.elamur.ai/free/en/papers/zheng-2026-njustkmg-semeval-2026-task-10/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/43/)

## References

50 references, 20 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Duarte M. Alves, José Pombal, Nuno Miguel Guerreiro, Pedro Henrique Martins, João Alves, M. Amin Farajian, Ben Peters, Ricardo Rei, Patrick Fernandes, Sweta Agrawal, Pierre Colombo, José G. C. de Souza, and André F. T. Martins. 2024. [Tower: An open multilingual large language model for translation-r…](https://md.research.elamur.ai/free/en/papers/alves-2024-tower-open-multilingual-large-language/)
2. Naveen Arivazhagan, Ankur Bapna, Orhan Firat, Dmitry Lepikhin, Melvin Johnson, Maxim Krikun, Mia Xu Chen, Yuan Cao, George F. Foster, Colin Cherry, Wolfgang Macherey, Zhifeng Chen, and Yonghui Wu. 2019. [Massively multilingual neural machine translation in the wild: Findings and challenges](https://md.research.elamur.ai/free/en/papers/arivazhagan-2019-massively-multilingual-neural-machine-translation/). CoRR, abs…
3. Mikko Aulamo, Sami Virpioja, and Jörg Tiedemann. 2020. OpusFilter: A configurable parallel corpus filtering toolbox. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pages 150–156. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Mikko+Aulamo%2C+Sami+Virpioja%2C+and+J%C3%B6rg+Tiedemann%2E+2020%2E+OpusFilter%3A+A+configurable+parallel+corpus+filtering+toolbox%2E+In+Proceedings+of+the+58th+Annual+Meeting+of+the+Association+for+Computational+Ling)
4. Laurie Burchell, Ona de Gibert, Nikolay Arefyev, Mikko Aulamo, Marta Bañón, Mariia Fedorova, Liane Guillou, Barry Haddow, Jan Hajič, Erik Henriksson, and 1 others. 2025. An expanded massive multilingual dataset for high-performance language technologies. arXiv preprint arXiv:2503.10267. — [arXiv:2503.10267](https://arxiv.org/abs/2503.10267) [find](https://scholar.google.com/scholar?q=Laurie+Burchell%2C+Ona+de+Gibert%2C+Nikolay+Arefyev%2C+Mikko+Aulamo%2C+Marta+Ba%C3%B1%C3%B3n%2C+Mariia+Fedorova%2C+Liane+Guillou%2C+Barry+Haddow%2C+Jan+Hajic%CC%8C%2C+Erik+Henriksson%2C+and+1+others%2E+2025%2E+An+expanded+massive+multiling)
5. Isaac Caswell, Elizabeth Nielsen, Jiaming Luo, Colin Cherry, Geza Kovacs, Hadar Shemtov, Partha Talukdar, Dinesh Tewari, Baba Mamadi Diane, Koulako Moussa Doumbouya, Djibrila Diane, Solo Farabado Cissé, Edoardo Ferrante, Alessandro Guasoni, Mamadou K. Keita, Sudhamoy Deb-Barma, Ali Kuzhuget, David A… — [arXiv:2502.12301](https://arxiv.org/abs/2502.12301) [find](https://scholar.google.com/scholar?q=Isaac+Caswell%2C+Elizabeth+Nielsen%2C+Jiaming+Luo%2C+Colin+Cherry%2C+Geza+Kovacs%2C+Hadar+Shemtov%2C+Partha+Talukdar%2C+Dinesh+Tewari%2C+Baba+Mamadi+Diane%2C+Koulako+Moussa+Doumbouya%2C+Djibrila+Diane%2C+Solo+Farabado+Ciss)
6. Andong Chen, Yuchen Song, Wenxin Zhu, Kehai Chen, Muyun Yang, Tiejun Zhao, and Min Zhang. 2025. Evaluating o1-like llms: Unlocking reasoning for translation through comprehensive analysis. CoRR, abs/2502.11544. [find](https://scholar.google.com/scholar?q=Andong+Chen%2C+Yuchen+Song%2C+Wenxin+Zhu%2C+Kehai+Chen%2C+Muyun+Yang%2C+Tiejun+Zhao%2C+and+Min+Zhang%2E+2025%2E+Evaluating+o1%2Dlike+llms%3A+Unlocking+reasoning+for+translation+through+comprehensive+analysis%2E+CoRR%2C+abs%2F2)
7. Shanbo Cheng, Yu Bao, Qian Cao, Luyang Huang, Liyan Kang, Zhicheng Liu, Yu Lu, Wenhao Zhu, Jingwen Chen, Zhichao Huang, Tao Li, Yifu Li, Huiying Lin, Sitong Liu, Ningxin Peng, Shuaijie She, Lu Xu, Nuo Xu, Sen Yang, and 7 others. 2025. Seed-x: Building strong multilingual translation LLM with 7b para… — [arXiv:2507.13618](https://arxiv.org/abs/2507.13618) [find](https://scholar.google.com/scholar?q=Shanbo+Cheng%2C+Yu+Bao%2C+Qian+Cao%2C+Luyang+Huang%2C+Liyan+Kang%2C+Zhicheng+Liu%2C+Yu+Lu%2C+Wenhao+Zhu%2C+Jingwen+Chen%2C+Zhichao+Huang%2C+Tao+Li%2C+Yifu+Li%2C+Huiying+Lin%2C+Sitong+Liu%2C+Ningxin+Peng%2C+Shuaijie+She%2C+Lu+Xu%2C+Nuo)
8. Marta R. Costa-jussà, James Cross, Onur Çelebi, Maha Elbayad, Kenneth Heafield, Kevin Heffernan, Elahe Kalbassi, Janice Lam, Daniel Licht, Jean Maillard, Anna Y. Sun, Skyler Wang, Guillaume Wenzek, Al Youngblood, Bapi Akula, Loïc Barrault, Gabriel Mejia Gonzalez, Prangthip Hansanti, John Hoffman, an… [find](https://scholar.google.com/scholar?q=Marta+R%2E+Costa%2Djuss%C3%A0%2C+James+Cross%2C+Onur+%C3%87elebi%2C+Maha+Elbayad%2C+Kenneth+Heafield%2C+Kevin+Heffernan%2C+Elahe+Kalbassi%2C+Janice+Lam%2C+Daniel+Licht%2C+Jean+Maillard%2C+Anna+Y%2E+Sun%2C+Skyler+Wang%2C+Guillaume+Wenzek%2C+Al)
9. Archi Mitra, Archie Sravankumar, Artem Korenev, Arthur Hinsvark, Arun Rao, Aston Zhang, and 82 others. 2024. [The llama 3 herd of models](https://md.research.elamur.ai/free/en/papers/grattafiori-2024-llama-3-herd-models/). CoRR, abs/2407.21783.
10. Angela Fan, Shruti Bhosale, Holger Schwenk, Zhiyi Ma, Ahmed El-Kishky, Siddharth Goyal, Mandeep Baines, Onur Celebi, Guillaume Wenzek, Vishrav Chaudhary, Naman Goyal, Tom Birch, Vitaliy Liptchinsky, Sergey Edunov, Michael Auli, and Armand Joulin. 2021. Beyond english-centric multilingual machine tra… [find](https://scholar.google.com/scholar?q=Angela+Fan%2C+Shruti+Bhosale%2C+Holger+Schwenk%2C+Zhiyi+Ma%2C+Ahmed+El%2DKishky%2C+Siddharth+Goyal%2C+Mandeep+Baines%2C+Onur+Celebi%2C+Guillaume+Wenzek%2C+Vishrav+Chaudhary%2C+Naman+Goyal%2C+Tom+Birch%2C+Vitaliy+Liptchinsky%2C+S)
11. Christian Federmann, Tom Kocmi, and Ying Xin. 2022. [NTREX-128 – news test references for MT evaluation of 128 languages](https://md.research.elamur.ai/free/en/papers/federmann-2022-ntrex-128-news-test-references/). In Proceedings of the First Workshop on Scaling Up Multilingual Evaluation, pages 21–24, Online. Association for Computational Linguistics.
12. Jiaxin Guo, Hao Yang, Zongyao Li, Daimeng Wei, Hengchao Shang, and Xiaoyu Chen. 2024. A novel paradigm boosting translation capabilities of large language models. In NAACL-HLT (Findings), pages 639–649. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Jiaxin+Guo%2C+Hao+Yang%2C+Zongyao+Li%2C+Daimeng+Wei%2C+Hengchao+Shang%2C+and+Xiaoyu+Chen%2E+2024%2E+A+novel+paradigm+boosting+translation+capabilities+of+large+language+models%2E+In+NAACL%2DHLT+%28Findings%29%2C+pages+639%E2%80%9364)
13. HuggingFaceFW. 2024. fineweb (revision af075be). [find](https://scholar.google.com/scholar?q=HuggingFaceFW%2E+2024%2E+fineweb+%28revision+af075be%29%2E)
14. Vivek Iyer, Bhavitvya Malik, Pavel Stepachev, Pinzhen Chen, Barry Haddow, and Alexandra Birch. 2024. [Quality or quantity? on data scale and diversity in adapting large language models for low-resource translation](https://md.research.elamur.ai/free/en/papers/iyer-2024-quality-quantity-data-scale-diversity/). In WMT, pages 1393–1409. Association for Computational Linguistics.
15. Menglong Cui, Pengzhi Gao, Wei Liu, Jian Luan, and Bin Wang. 2025. Multilingual machine translation with open large language models at practical scale: An empirical study. In NAACL (Long Papers), pages 5420–5443. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Menglong+Cui%2C+Pengzhi+Gao%2C+Wei+Liu%2C+Jian+Luan%2C+and+Bin+Wang%2E+2025%2E+Multilingual+machine+translation+with+open+large+language+models+at+practical+scale%3A+An+empirical+study%2E+In+NAACL+%28Long+Papers%29%2C+page)
16. Sneha Kudugunta, Isaac Caswell, Biao Zhang, Xavier Garcia, Christopher A. Choquette-Choo, Katherine Lee, Derrick Xin, Aditya Kusupati, Romi Stella, Ankur Bapna, and Orhan Firat. 2023. [Madlad-400: A multilingual and document-level large audited dataset](https://md.research.elamur.ai/free/en/papers/kudugunta-2023-madlad-400-multilingual-document-level/). Preprint, arXiv:2309.04662.
17. John Dang, Shivalika Singh, Daniel D’souza, Arash Ahmadian, Alejandro Salamanca, Madeline Smith, Aidan Peppin, Sungjin Hong, Manoj Govindassamy, Terrence Zhao, Sandra Kublik, Meor Amer, Viraat Aryabumi, Jon Ander Campos, Yi-Chern Tan, Tom Kocmi, Florian Strub, Nathan Grinsztajn, Yannis Flet-Berliac,… — [Aya Expanse: Combining Research Breakthroughs for a New Multilingual Frontier](https://md.research.elamur.ai/free/en/papers/dang-2024-aya-expanse-combining-research-breakthroughs/)
18. Yinquan Lu, Wenhao Zhu, Lei Li, Yu Qiao, and Fei Yuan. 2024. LLaMAX: Scaling linguistic horizons of LLM by enhancing translation capabilities beyond 100 languages. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 10748–10772, Miami, Florida, USA. Association for Comput… [find](https://scholar.google.com/scholar?q=Yinquan+Lu%2C+Wenhao+Zhu%2C+Lei+Li%2C+Yu+Qiao%2C+and+Fei+Yuan%2E+2024%2E+LLaMAX%3A+Scaling+linguistic+horizons+of+LLM+by+enhancing+translation+capabilities+beyond+100+languages%2E+In+Findings+of+the+Association+for+C)
19. Daniel Deutsch, Eleftheria Briakou, Isaac Caswell, Mara Finkelstein, Rebecca Galor, Juraj Juraska, Geza Kovacs, Alison Lui, Ricardo Rei, Jason Riesa, Shruti Rijhwani, Parker Riley, Elizabeth Salesky, Firas Trabelsi, Stephanie Winkler, Biao Zhang, and Markus Freitag. 2025. [WMT24++: Expanding the Lang…](https://md.research.elamur.ai/free/en/papers/deutsch-2025-wmt24-expanding-language-coverage-wmt24/)
20. Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, Anirudh Goyal, Anthony Hartshorn, Aobo Yang, Yingfeng Luo, Tong Zheng, Yongyu Mu, Bei Li, Qinghong Zhang, Yongqi Gao, Ziqiang Xu, Peinan Feng, Xiaoqian… [find](https://scholar.google.com/scholar?q=Abhimanyu+Dubey%2C+Abhinav+Jauhri%2C+Abhinav+Pandey%2C+Abhishek+Kadian%2C+Ahmad+Al%2DDahle%2C+Aiesha+Letman%2C+Akhil+Mathur%2C+Alan+Schelten%2C+Amy+Yang%2C+Angela+Fan%2C+Anirudh+Goyal%2C+Anthony+Hartshorn%2C+Aobo+Yang%2C+Yingfen)
21. Yongyu Mu, Peinan Feng, Zhiquan Cao, Yuzhang Wu, Bei Li, Chenglong Wang, Tong Xiao, Kai Song, Tongran Liu, Chunliang Zhang, and JingBo Zhu. 2024. Revealing the parallel multilingual learning within large language models. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language… [find](https://scholar.google.com/scholar?q=Yongyu+Mu%2C+Peinan+Feng%2C+Zhiquan+Cao%2C+Yuzhang+Wu%2C+Bei+Li%2C+Chenglong+Wang%2C+Tong+Xiao%2C+Kai+Song%2C+Tongran+Liu%2C+Chunliang+Zhang%2C+and+JingBo+Zhu%2E+2024%2E+Revealing+the+parallel+multilingual+learning+within+la)
22. Thuat Nguyen, Chien Van Nguyen, Viet Dac Lai, Hieu Man, Nghia Trung Ngo, Franck Dernoncourt, Ryan A. Rossi, and Thien Huu Nguyen. 2023. [Culturax: A cleaned, enormous, and multilingual dataset for large language models in 167 languages](https://md.research.elamur.ai/free/en/papers/nguyen-2023-culturax-cleaned-enormous-multilingual-dataset/). Preprint, arXiv:2309.09400.
23. Thuat Nguyen, Chien Van Nguyen, Viet Dac Lai, Hieu Man, Nghia Trung Ngo, Franck Dernoncourt, Ryan A. Rossi, and Thien Huu Nguyen. 2024. [CulturaX: A cleaned, enormous, and multilingual dataset for large language models in 167 languages](https://md.research.elamur.ai/free/en/papers/nguyen-2023-culturax-cleaned-enormous-multilingual-dataset/). In Proceedings of the 2024 Joint International Conference on Com…
24. Yuta Nishimura, Katsuhito Sudoh, Graham Neubig, and Satoshi Nakamura. 2020. Multi-source neural machine translation with missing data. IEEE ACM Trans. Audio Speech Lang. Process., 28:569–580. [find](https://scholar.google.com/scholar?q=Yuta+Nishimura%2C+Katsuhito+Sudoh%2C+Graham+Neubig%2C+and+Satoshi+Nakamura%2E+2020%2E+Multi%2Dsource+neural+machine+translation+with+missing+data%2E+IEEE+ACM+Trans%2E+Audio+Speech+Lang%2E+Process%2E%2C+28%3A569%E2%80%93580%2E)
25. Matt Post. 2018. [A call for clarity in reporting BLEU scores](https://md.research.elamur.ai/free/en/papers/post-2018-call-clarity-reporting-bleu-scores/). In Proceedings of the Third Conference on Machine Translation: Research Papers, pages 186– 191, Belgium, Brussels. Association for Computational Linguistics.
26. Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2020. [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.
27. Ricardo Rei, José G. C. de Souza, Duarte M. Alves, Chrysoula Zerva, Ana C. Farinha, Taisiya Glushkova, Alon Lavie, Luísa Coheur, and André F. T. Martins. 2022a. [COMET-22: unbabel-ist 2022 submission for the metrics shared task](https://md.research.elamur.ai/free/en/papers/rei-2022-comet-22-unbabel-ist-2022/). In WMT, pages 578–585. Association for Computational Linguistics.
28. Ricardo Rei, Marcos V. Treviso, Nuno Miguel Guerreiro, Chrysoula Zerva, Ana C. Farinha, Christine Maroti, José G. C. de Souza, Taisiya Glushkova, Duarte M. Alves, Luísa Coheur, Alon Lavie, and André F. T. Martins. 2022b. [find](https://scholar.google.com/scholar?q=Ricardo+Rei%2C+Marcos+V%2E+Treviso%2C+Nuno+Miguel+Guerreiro%2C+Chrysoula+Zerva%2C+Ana+C%2E+Farinha%2C+Christine+Maroti%2C+Jos%C3%A9+G%2E+C%2E+de+Souza%2C+Taisiya+Glushkova%2C+Duarte+M%2E+Alves%2C+Lu%C3%ADsa+Coheur%2C+Alon+Lavie%2C+and+Andr%C3%A9+F)
29. [Cometkiwi: Ist-unbabel 2022 submission for the quality estimation shared task](https://md.research.elamur.ai/free/en/papers/rei-2022-cometkiwi-ist-unbabel-2022-submission/). In WMT, pages 634–645. Association for Computational Linguistics.
30. Morgane Rivière, Shreya Pathak, Pier Giuseppe Sessa, Cassidy Hardin, Surya Bhupatiraju, Léonard Hussenot, Thomas Mesnard, Bobak Shahriari, Alexandre Ramé, Johan Ferret, Peter Liu, Pouya Tafti, Abe Friesen, Michelle Casbon, Sabela Ramos, Ravin Kumar, Charline Le Lan, Sammy Jerome, Anton Tsitsulin, an… [find](https://scholar.google.com/scholar?q=Morgane+Rivi%C3%A8re%2C+Shreya+Pathak%2C+Pier+Giuseppe+Sessa%2C+Cassidy+Hardin%2C+Surya+Bhupatiraju%2C+L%C3%A9onard+Hussenot%2C+Thomas+Mesnard%2C+Bobak+Shahriari%2C+Alexandre+Ram%C3%A9%2C+Johan+Ferret%2C+Peter+Liu%2C+Pouya+Tafti%2C+Abe+Fri)
31. Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Mingchuan Zhang, Y. K. Li, Y. Wu, and Daya Guo. 2024. [Deepseekmath: Pushing the limits of mathematical reasoning in open language models](https://md.research.elamur.ai/free/en/papers/shao-2024-deepseekmath-pushing-limits-mathematical-reasoning/). CoRR, abs/2402.03300.
32. Yingli Shen, Wen Lai, Shuo Wang, Kangyang Luo, Alexander Fraser, and Maosong Sun. 2025. From unaligned to aligned: Scaling multilingual llms with multi-way parallel corpora. CoRR, abs/2505.14045. [find](https://scholar.google.com/scholar?q=Yingli+Shen%2C+Wen+Lai%2C+Shuo+Wang%2C+Kangyang+Luo%2C+Alexander+Fraser%2C+and+Maosong+Sun%2E+2025%2E+From+unaligned+to+aligned%3A+Scaling+multilingual+llms+with+multi%2Dway+parallel+corpora%2E+CoRR%2C+abs%2F2505%2E14045%2E)
33. Daria Soboleva, Faisal Al-Khateeb, Robert Myers, Jacob R Steeves, Joel Hestness, and Nolan Dey. 2023. SlimPajama: A 627B token cleaned and deduplicated version of RedPajama. [https://www.cerebras.net/blog/slimpajama-a-627b-token-cleaned-a](https://www.cerebras.net/blog/slimpajama-a-627b-token-cleaned-a) nd-deduplicated-version-of-redpajama. [↗](https://www.cerebras.net/blog/slimpajama-a-627b-token-cleaned-a)
34. Jiaan Wang, Fandong Meng, Yunlong Liang, and Jie Zhou. 2025a. DRT: deep reasoning translation via long chain-of-thought. In Findings of the Association for Computational Linguistics, ACL 2025, Vienna, Austria, July 27 - August 1, 2025, pages 6770–6782. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Jiaan+Wang%2C+Fandong+Meng%2C+Yunlong+Liang%2C+and+Jie+Zhou%2E+2025a%2E+DRT%3A+deep+reasoning+translation+via+long+chain%2Dof%2Dthought%2E+In+Findings+of+the+Association+for+Computational+Linguistics%2C+ACL+2025%2C+Vienna%2C)
35. Longyue Wang, Zefeng Du, Wenxiang Jiao, Chenyang Lyu, Jianhui Pang, Leyang Cui, Kaiqiang Song, Derek F. Wong, Shuming Shi, and Zhaopeng Tu. 2024. Benchmarking and improving long-text translation with large language models. In Findings of the Association for Computational Linguistics, ACL 2024, Bangk… [find](https://scholar.google.com/scholar?q=Longyue+Wang%2C+Zefeng+Du%2C+Wenxiang+Jiao%2C+Chenyang+Lyu%2C+Jianhui+Pang%2C+Leyang+Cui%2C+Kaiqiang+Song%2C+Derek+F%2E+Wong%2C+Shuming+Shi%2C+and+Zhaopeng+Tu%2E+2024%2E+Benchmarking+and+improving+long%2Dtext+translation+with+)
36. Yutong Wang, Jiali Zeng, Xuebo Liu, Derek F. Wong, Fandong Meng, Jie Zhou, and Min Zhang. 2025b. Delta: An online document-level translation agent based on multi-level memory. In The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025. OpenReview.… [find](https://scholar.google.com/scholar?q=Yutong+Wang%2C+Jiali+Zeng%2C+Xuebo+Liu%2C+Derek+F%2E+Wong%2C+Fandong+Meng%2C+Jie+Zhou%2C+and+Min+Zhang%2E+2025b%2E+Delta%3A+An+online+document%2Dlevel+translation+agent+based+on+multi%2Dlevel+memory%2E+In+The+Thirteenth+Intern)
37. Tianwen Wei, Liang Zhao, Lichang Zhang, Bo Zhu, Lijie Wang, Haihua Yang, Biye Li, Cheng Cheng, Weiwei Lü, Rui Hu, Chenxia Li, Liu Yang, Xilin Luo, Xuejie Wu, Lunan Liu, Wenjun Cheng, Peng Cheng, Jianhao Zhang, Xiaoyu Zhang, and 11 others. 2023. [Skywork: A more open bilingual foundation model](https://md.research.elamur.ai/free/en/papers/wei-2023-skywork-more-open-bilingual/). Prepri…
38. Haoran Xu, Young Jin Kim, Amr Sharaf, and Hany Hassan Awadalla. 2024. A paradigm shift in machine translation: Boosting translation performance of large language models. In ICLR. OpenReview.net. [find](https://scholar.google.com/scholar?q=Haoran+Xu%2C+Young+Jin+Kim%2C+Amr+Sharaf%2C+and+Hany+Hassan+Awadalla%2E+2024%2E+A+paradigm+shift+in+machine+translation%3A+Boosting+translation+performance+of+large+language+models%2E+In+ICLR%2E+OpenReview%2Enet%2E)
39. Haoran Xu, Kenton Murray, Philipp Koehn, Hieu Hoang, Akiko Eriguchi, and Huda Khayrallah. 2025. X-ALMA: plug & play modules and adaptive rejection for quality translation at scale. In ICLR. Open-Review.net. [find](https://scholar.google.com/scholar?q=Haoran+Xu%2C+Kenton+Murray%2C+Philipp+Koehn%2C+Hieu+Hoang%2C+Akiko+Eriguchi%2C+and+Huda+Khayrallah%2E+2025%2E+X%2DALMA%3A+plug+%26+play+modules+and+adaptive+rejection+for+quality+translation+at+scale%2E+In+ICLR%2E+Open%2DRevie)
40. Weijia Xu, Yuwei Yin, Shuming Ma, Dongdong Zhang, and Haoyang Huang. 2021. Improving multilingual neural machine translation with auxiliary source languages. In Findings of the Association for Computational Linguistics: EMNLP 2021, Virtual Event / Punta Cana, Dominican Republic, 16-20 November, 2021… [find](https://scholar.google.com/scholar?q=Weijia+Xu%2C+Yuwei+Yin%2C+Shuming+Ma%2C+Dongdong+Zhang%2C+and+Haoyang+Huang%2E+2021%2E+Improving+multilingual+neural+machine+translation+with+auxiliary+source+languages%2E+In+Findings+of+the+Association+for+Computa)
41. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, Chujie Zheng, Dayiheng Liu, Fan Zhou, Fei Huang, Feng Hu, Hao Ge, Haoran Wei, Huan Lin, Jialong Tang, and 41 others. 2025a. [Qwen3 technical report](https://md.research.elamur.ai/free/en/papers/yang-2025-qwen3-technical-report/). CoRR, abs/2505.09388.
42. Sen Yang, Yu Bao, Yu Lu, Jiajun Chen, Shujian Huang, and Shanbo Cheng. 2025b. Enanchored-x2x: English-anchored optimization for many-to-many translation. CoRR, abs/2509.19770. [find](https://scholar.google.com/scholar?q=Sen+Yang%2C+Yu+Bao%2C+Yu+Lu%2C+Jiajun+Chen%2C+Shujian+Huang%2C+and+Shanbo+Cheng%2E+2025b%2E+Enanchored%2Dx2x%3A+English%2Danchored+optimization+for+many%2Dto%2Dmany+translation%2E+CoRR%2C+abs%2F2509%2E19770%2E)
43. Wen Yang, Chong Li, Jiajun Zhang, and Chengqing Zong. 2023. Bigtrans: Augmenting large language models with multilingual translation capability over 100 languages. CoRR, abs/2305.18098. — [arXiv:2305.18098](https://arxiv.org/abs/2305.18098) [find](https://scholar.google.com/scholar?q=Wen+Yang%2C+Chong+Li%2C+Jiajun+Zhang%2C+and+Chengqing+Zong%2E+2023%2E+Bigtrans%3A+Augmenting+large+language+models+with+multilingual+translation+capability+over+100+languages%2E+CoRR%2C+abs%2F2305%2E18098%2E+%E2%80%94+%5BarXiv%3A2305%2E)
44. Jia Yu, Fei Yuan, Rui Min, Jing Yu, Pei Chu, Jiayang Li, Wei Li, Ruijie Zhang, Zhenxiang Li, Zhifei Ren, Dong Zheng, Wenjian Zhang, Yan Teng, Lingyu Meng, ZhenJiang Jin, Jiantao Qiu, ShaSha Wang, Zhongying Tu, Dahua Lin, and 4 others. 2025. Wanjuansilu: A high-quality open-source webtext dataset for… — [arXiv:2501.14506](https://arxiv.org/abs/2501.14506) [find](https://scholar.google.com/scholar?q=Jia+Yu%2C+Fei+Yuan%2C+Rui+Min%2C+Jing+Yu%2C+Pei+Chu%2C+Jiayang+Li%2C+Wei+Li%2C+Ruijie+Zhang%2C+Zhenxiang+Li%2C+Zhifei+Ren%2C+Dong+Zheng%2C+Wenjian+Zhang%2C+Yan+Teng%2C+Lingyu+Meng%2C+ZhenJiang+Jin%2C+Jiantao+Qiu%2C+ShaSha+Wang%2C+Zhon)
45. Biao Zhang, Philip Williams, Ivan Titov, and Rico Sennrich. 2020. [Improving massively multilingual neural machine translation and zero-shot translation](https://md.research.elamur.ai/free/en/papers/zhang-2020-improving-massively-multilingual-neural-machine/). In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1628– 1639, Online. Association for Computational…
46. Mao Zheng, Jiaqiang Wang, Haoran Xiong, Hongda Liu, Canrong He, Ziyue Jiang, and Dingkai Long. 2025a. [Hunyuan-MT Technical Report](https://md.research.elamur.ai/free/en/papers/zheng-2025-hunyuan-mt-technical-report/). Preprint, arXiv:2509.05209.
47. Tong Zheng, Yan Wen, Huiwen Bao, Junfeng Guo, and Heng Huang. 2025b. Asymmetric conflict and synergy in post-training for llm-based multilingual machine translation. CoRR, abs/2502.11223. [find](https://scholar.google.com/scholar?q=Tong+Zheng%2C+Yan+Wen%2C+Huiwen+Bao%2C+Junfeng+Guo%2C+and+Heng+Huang%2E+2025b%2E+Asymmetric+conflict+and+synergy+in+post%2Dtraining+for+llm%2Dbased+multilingual+machine+translation%2E+CoRR%2C+abs%2F2502%2E11223%2E)
48. Chunting Zhou, Pengfei Liu, Puxin Xu, Srinivasan Iyer, Jiao Sun, Yuning Mao, Xuezhe Ma, Avia Efrat, Ping Yu, Lili Yu, Susan Zhang, Gargi Ghosh, Mike Lewis, Luke Zettlemoyer, and Omer Levy. 2023. LIMA: less is more for alignment. In NeurIPS. [find](https://scholar.google.com/scholar?q=Chunting+Zhou%2C+Pengfei+Liu%2C+Puxin+Xu%2C+Srinivasan+Iyer%2C+Jiao+Sun%2C+Yuning+Mao%2C+Xuezhe+Ma%2C+Avia+Efrat%2C+Ping+Yu%2C+Lili+Yu%2C+Susan+Zhang%2C+Gargi+Ghosh%2C+Mike+Lewis%2C+Luke+Zettlemoyer%2C+and+Omer+Levy%2E+2023%2E+LIMA%3A)
49. Dawei Zhu, Pinzhen Chen, Miaoran Zhang, Barry Haddow, Xiaoyu Shen, and Dietrich Klakow. 2024. Fine-tuning large language models to translate: Will a touch of noisy data in misaligned languages suffice? In EMNLP, pages 388–409. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Dawei+Zhu%2C+Pinzhen+Chen%2C+Miaoran+Zhang%2C+Barry+Haddow%2C+Xiaoyu+Shen%2C+and+Dietrich+Klakow%2E+2024%2E+Fine%2Dtuning+large+language+models+to+translate%3A+Will+a+touch+of+noisy+data+in+misaligned+languages+suffice)
50. Ahmet Üstün, Viraat Aryabumi, Zheng-Xin Yong, Wei-Yin Ko, Daniel D’souza, Gbemileke Onilude, Neel Bhandari, Shivalika Singh, Hui-Lee Ooi, Amr Kayid, Freddie Vargus, Phil Blunsom, Shayne Longpre, Niklas Muennighoff, Marzieh Fadaee, Julia Kreutzer, and Sara Hooker. 2024. [Aya model: An instruction fine…](https://md.research.elamur.ai/free/en/papers/ustun-2024-aya-model-instruction-finetuned-open/)

*Updated 1 November 2026*