---
title: "Eliciting the Translation Ability of Large Language Models via"
description: "The authors test a different approach, multilingual Finetuning with Translation Instructions (mFTI). 37 references, cited by 45 papers here."
authors: ["Jiahuan Li", "Hao Zhou", "Shujian Huang", "Shanbo Cheng", "Jiajun Chen"]
year: 2024
venue: "Transactions of the Association for Computational Linguistics"
source: "https://aclanthology.org/2024.tacl-1.32/"
doi: "10.1162/tacl_a_00655"
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/li-2024-eliciting-translation-ability-large-language/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/li-2024-eliciting-translation-ability-large-language/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2024](https://md.research.elamur.ai/free/en/papers/2024/page/3/) / Eliciting the Translation Ability of Large Language Models via Multilingual Finetuning with Translation Instructions

# Eliciting the Translation Ability of Large Language Models via Multilingual Finetuning with Translation Instructions

**Authors:** Jiahuan Li, [Hao Zhou](https://md.research.elamur.ai/free/en/authors/hao-zhou/), [Shujian Huang](https://md.research.elamur.ai/free/en/authors/shujian-huang/), Shanbo Cheng and [Jiajun Chen](https://md.research.elamur.ai/free/en/authors/jiajun-chen/) · **Year:** 2024 · **Venue:** [Transactions of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/tacl/) ([Transactions of the Association for Computational Linguistics (TACL) 2024](https://md.research.elamur.ai/free/en/venues/tacl/2024/)) · **Publisher:** [The MIT Press](https://md.research.elamur.ai/free/en/publishers/the-mit-press/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2024.tacl-1.32/) · [PDF](https://aclanthology.org/2024.tacl-1.32.pdf) · [DOI 10.1162/tacl\_a\_00655](https://doi.org/10.1162/tacl_a_00655) · [OpenAlex](https://openalex.org/W4395680645)

**Citations:** 54 citations (OpenAlex, 2026-10-14) · [45](https://md.research.elamur.ai/free/en/papers/li-2024-eliciting-translation-ability-large-language/cited-by/) in our library, of the 141,840 papers whose bibliographies we read

## Summary
Prior work on machine translation with LLMs mostly relies on few-shot in-context learning (ICL). For mid-sized models, weak ICL may hide how well they can actually translate. The authors test a different approach, multilingual Finetuning with Translation Instructions (mFTI). They cast each language pair as an instance of a single translation prompt and finetune XGLM-7.5B with a standard next-token objective. The training data is small: 1,000 parallel sentences per direction, drawn from WikiMatrix and, for a few Swahili pairs, MultiCCAligned. It covers 13 languages and 156 directions, with evaluation on FLORES-101.

mFTI beats 8-shot ICL in every direction. The analysis also explains why it works: the model learns to follow the instruction format and to align languages directly, rather than going through English. This lets it translate reasonably even for pairs it never saw during finetuning. The work matters because it shows that cheap instruction finetuning can unlock latent multilingual translation skill. It also shows that a language's typological closeness to English predicts quality better than its share of the pretraining data.

## Key points
- **Main gain:** with 1,000 sentences per pair, mFTI outperforms 8-shot ICL by about 3 BLEU on average. The gain reaches up to 8 BLEU for translation into Catalan, while gains are smaller for directions involving English.
- **English-centric behavior:** Spearman correlations show that similarity to English predicts BLEU better than pretraining data volume. Similarity was measured via lang2vec/URIEL, with geography at 0.93/0.87 (to/from X). Pretraining data volume correlates at only 0.39/0.36.
- **Consistency across setups:** the advantage over ICL holds on BLOOM-7b1 and LLaMA-7B, under both sacreBLEU and COMET. XGLM-7.5B is the strongest of the three, and full finetuning beat LoRA when training on 156 directions.
- **Generalization to unseen pairs:** mFTI generalizes to language pairs absent from finetuning. Adding unrelated language pairs and monolingual sentences reduces off-target output, and learning from pivot-language pairs strengthens direct alignment.
- **Remaining errors in zero-shot translation:** over- and under-translation, oscillatory hallucination, and mistranslations caused by wrong alignments.

*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

- [ByteDance](https://md.research.elamur.ai/free/en/companies/bytedance/) — Company, Beijing, China · 18 works · 3,890 citations
- [Nanjing University](https://md.research.elamur.ai/free/en/universities/nanjing-university/) — University, Nanjing, China · 28 works · 7,072 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 9,085 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 8,888 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 9,296 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 9,206 works

🧭 Topics (1): [🌍 Multilingual & cross-lingual NLP](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/) · 465 works

## Cite

Cite as: Jiahuan Li, Hao Zhou, Shujian Huang, Shanbo Cheng and Jiajun Chen. 2024. Eliciting the Translation Ability of Large Language Models via Multilingual Finetuning with Translation Instructions. Transactions of the Association for Computational Linguistics.

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

```bibtex
@article{li2024eliciting,
  title = {{Eliciting the Translation Ability of Large Language Models via Multilingual Finetuning with Translation Instructions}},
  author = {Jiahuan Li, Hao Zhou, Shujian Huang, Shanbo Cheng and Jiajun Chen},
  journal = {Transactions of the Association for Computational Linguistics},
  year = {2024},
  doi = {10.1162/tacl\_a\_00655},
  url = {https://doi.org/10.1162/tacl_a_00655}
}
```

- [← previous Disentangling Length from Quality in Direct Preference Optimization](https://md.research.elamur.ai/free/en/papers/park-2024-disentangling-length-quality-direct-preference/)
- [next → Do Multilingual Language Models Think Better in English?](https://md.research.elamur.ai/free/en/papers/etxaniz-2024-do-multilingual-language-models-think/)
- [↑ back to papers of 2024](https://md.research.elamur.ai/free/en/papers/2024/page/3/)

## References

37 references, 15 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Sweta Agrawal, Chunting Zhou, Mike Lewis, Luke Zettlemoyer, and Marjan Ghazvininejad. 2023. [In-context examples selection for machine translation](https://md.research.elamur.ai/free/en/papers/agrawal-2023-context-examples-selection-machine-translation/). In Findings of the Association for Computational Linguistics: ACL 2023, pages 8857–8873, Toronto, Canada. Association for Computational Linguistics. http…
2. Marta R. Costa-jussà, James Cross, Onur Çelebi, Maha Elbayad, Kenneth Heafield, Kevin Heffernan, Elahe Kalbassi, Janice Lam, Daniel Licht, Jean Maillard, Anna Sun, Skyler Wang, Guillaume Wenzek, Al Youngblood, Bapi Akula, Loic Barrault, Gabriel Mejia Gonzalez, Prangthip Hansanti, John Hoffman, Sem… [find](https://scholar.google.com/scholar?q=Marta+R%2E+Costa%2Djussa%CC%80%2C+James+Cross%2C+Onur+C%CC%A7elebi%2C+Maha+Elbayad%2C+Kenneth+Heafield%2C+Kevin+Heffernan%2C+Elahe+Kalbassi%2C+Janice+Lam%2C+Daniel+Licht%2C+Jean+Maillard%2C+Anna+Sun%2C+Skyler+Wang%2C+Guillaume+Wenzek%2C+Al+)
3. Maruan Al-Shedivat and Ankur Parikh. 2019. Consistency by agreement in zero-shot neural machine translation. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 1184… [find](https://scholar.google.com/scholar?q=Maruan+Al%2DShedivat+and+Ankur+Parikh%2E+2019%2E+Consistency+by+agreement+in+zero%2Dshot+neural+machine+translation%2E+In+Proceedings+of+the+2019+Conference+of+the+North+American+Chapter+of+the+Association+for+)
4. Ahmed El-Kishky, Vishrav Chaudhary, Francisco Guzman, and Philipp Koehn. 2020. [CCAligned: A massive collection of cross-lingual web-document pairs](https://md.research.elamur.ai/free/en/papers/kishky-2020-ccaligned-massive-collection-cross-lingual/). In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP 2020), pages 5960–5969, Online. Association for Computa…
5. Naveen Arivazhagan, Ankur Bapna, Orhan Firat, Roee Aharoni, Melvin Johnson, and Wolfgang Macherey. 2019. The missing ingredient in zero-shot neural machine translation. CoRR, cs.CL/1903.07091v1. [find](https://scholar.google.com/scholar?q=Naveen+Arivazhagan%2C+Ankur+Bapna%2C+Orhan+Firat%2C+Roee+Aharoni%2C+Melvin+Johnson%2C+and+Wolfgang+Macherey%2E+2019%2E+The+missing+ingredient+in+zero%2Dshot+neural+machine+translation%2E+CoRR%2C+cs%2ECL%2F1903%2E07091v1%2E)
6. Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, T. J. Henighan, Rewon Child, Aditya Ramesh, Daniel M. Ziegler, Jeff Wu, Clemens Winter, C… — [Language Models are Few-Shot Learners](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/)
7. 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, Edouard Grave, Michael Auli, and Armand Joulin. 2020. Beyond English-centric multiling… [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)
8. Xavier Garcia, Yamini Bansal, Colin Cherry, George Foster, Maxim Krikun, Fangxiaoyu Feng, Melvin Johnson, and Orhan Firat. 2023. The unreasonable effectiveness of few-shot learning for machine translation. CoRR, cs.CL/2302.01398v1. [find](https://scholar.google.com/scholar?q=Xavier+Garcia%2C+Yamini+Bansal%2C+Colin+Cherry%2C+George+Foster%2C+Maxim+Krikun%2C+Fangxiaoyu+Feng%2C+Melvin+Johnson%2C+and+Orhan+Firat%2E+2023%2E+The+unreasonable+effectiveness+of+few%2Dshot+learning+for+machine+transla)
9. Dario Amodei. 2020. [Scaling laws for neural language models](https://md.research.elamur.ai/free/en/papers/kaplan-2020-scaling-laws-neural-language-models/). CoRR, cs.LG/2001.08361v1.
10. Diederik P. Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. CoRR, cs.LG/1412.6980v9. [find](https://scholar.google.com/scholar?q=Diederik+P%2E+Kingma+and+Jimmy+Ba%2E+2014%2E+Adam%3A+A+method+for+stochastic+optimization%2E+CoRR%2C+cs%2ELG%2F1412%2E6980v9%2E)
11. Naman Goyal, Cynthia Gao, Vishrav Chaudhary, Peng-Jen Chen, Guillaume Wenzek, Da Ju, Sanjana Krishnan, Marc’Aurelio Ranzato, Francisco Guzmán, and Angela Fan. 2022. The Flores-101 evaluation benchmark for low-resource and multilingual machine translation. Transactions of the Association for Computa… [find](https://scholar.google.com/scholar?q=Naman+Goyal%2C+Cynthia+Gao%2C+Vishrav+Chaudhary%2C+Peng%2DJen+Chen%2C+Guillaume+Wenzek%2C+Da+Ju%2C+Sanjana+Krishnan%2C+Marc%E2%80%99Aurelio+Ranzato%2C+Francisco+Guzma%CC%81n%2C+and+Angela+Fan%2E+2022%2E+The+Flores%2D101+evaluation+benchmar)
12. Xi Victoria Lin, Todor Mihaylov, Mikel Artetxe, Tianlu Wang, Shuohui Chen, Daniel Simig, Myle Ott, Naman Goyal, Shruti Bhosale, Jingfei Du, Ramakanth Pasunuru, Sam Shleifer, Punit Singh Koura, Vishrav Chaudhary, Brian O’Horo, Jeff Wang, Luke Zettlemoyer, Zornitsa Kozareva, Mona Diab, Veselin Stoyano… [find](https://scholar.google.com/scholar?q=Xi+Victoria+Lin%2C+Todor+Mihaylov%2C+Mikel+Artetxe%2C+Tianlu+Wang%2C+Shuohui+Chen%2C+Daniel+Simig%2C+Myle+Ott%2C+Naman+Goyal%2C+Shruti+Bhosale%2C+Jingfei+Du%2C+Ramakanth+Pasunuru%2C+Sam+Shleifer%2C+Punit+Singh+Koura%2C+Vishrav)
13. Jiatao Gu, Yong Wang, Kyunghyun Cho, and Victor O. K. Li. 2019. [Improved zero-shot neural machine translation via ignoring spurious correlations](https://md.research.elamur.ai/free/en/papers/gu-2019-improved-zero-shot-neural-machine/). In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 1258–1268, Florence, Italy. Association for Computationa…
14. Patrick Littell, David R. Mortensen, Ke Lin, Katherine Kairis, Carlisle Turner, and Lori Levin. 2017. [URIEL and lang2vec: Representing languages as typological, geographical, and phylogenetic vectors](https://md.research.elamur.ai/free/en/papers/littell-2017-uriel-lang2vec-representing-languages-as/). In Proceedings of the 15th Conference of the European Chapter of the Association for Computational…
15. Amr Hendy, Mohamed Abdelrehim, Amr Sharaf, Vikas Raunak, Mohamed Gabr, Hitokazu Matsushita, Young Jin Kim, Mohamed Afify, and Hany Hassan Awadalla. 2023. How good are GPT models at machine translation? A comprehensive evaluation. CoRR, cs.CL/2302 .09210v1. [find](https://scholar.google.com/scholar?q=Amr+Hendy%2C+Mohamed+Abdelrehim%2C+Amr+Sharaf%2C+Vikas+Raunak%2C+Mohamed+Gabr%2C+Hitokazu+Matsushita%2C+Young+Jin+Kim%2C+Mohamed+Afify%2C+and+Hany+Hassan+Awadalla%2E+2023%2E+How+good+are+GPT+models+at+machine+translation)
16. Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. [LoRA: Low-rank adaptation of large language models](https://md.research.elamur.ai/free/en/papers/hu-2021-lora-low-rank-adaptation-large/). In International Conference on Learning Representations.
17. Hui Liu, Danqing Zhang, Bing Yin, and Xiaodan Zhu. 2021. Improving pretrained models for zero-shot multi-label text classification through reinforced label hierarchy reasoning. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human… [find](https://scholar.google.com/scholar?q=Hui+Liu%2C+Danqing+Zhang%2C+Bing+Yin%2C+and+Xiaodan+Zhu%2E+2021%2E+Improving+pretrained+models+for+zero%2Dshot+multi%2Dlabel+text+classification+through+reinforced+label+hierarchy+reasoning%2E+In+Proceedings+of+the+2)
18. Wenxiang Jiao, Jen tse Huang, Wenxuan Wang, Xing Wang, Shuming Shi, and Zhaopeng Tu. 2023b. ParroT: Translating during chat using large language models. CoRR, cs.CL/2304.02426v4. [find](https://scholar.google.com/scholar?q=Wenxiang+Jiao%2C+Jen+tse+Huang%2C+Wenxuan+Wang%2C+Xing+Wang%2C+Shuming+Shi%2C+and+Zhaopeng+Tu%2E+2023b%2E+ParroT%3A+Translating+during+chat+using+large+language+models%2E+CoRR%2C+cs%2ECL%2F2304%2E02426v4%2E)
19. Wenxiang Jiao, Wenxuan Wang, Jen tse Huang, Xing Wang, and Zhaopeng Tu. 2023b. [Is ChatGPT a good translator? Yes with GPT-4 as the engine](https://md.research.elamur.ai/free/en/papers/jiao-2023-chatgpt-good-translator-yes-gpt/). CoRR, cs.CL/2301.08745v3.
20. Niklas Muennighoff, Thomas Wang, Lintang Sutawika, Adam Roberts, Stella Biderman, Teven Le Scao, M. Saiful Bari, Sheng Shen, Zheng-Xin Yong, Hailey Schoelkopf, Xiangru Tang, Dragomir Radev, Alham Fikri Aji, Khalid Almubarak, Samuel Albanie, Zaid Alyafeai, Albert Webson, Edward Raff, and Colin Raffel… — [Crosslingual Generalization through Multitask Finetuning](https://md.research.elamur.ai/free/en/papers/muennighoff-2022-crosslingual-generalization-through-multitask-finetuning/)
21. Computational Linguistics. https://doi.org/10.18653/v1/2021.eacl-main.115 — [doi:10.18653/v1/2021.eacl-main.115](https://doi.org/10.18653/v1/2021.eacl-main.115) [↗](https://doi.org/10.18653/v1/2021.eacl-main.115)
22. OpenAI. 2023. Chatgpt (mar 23 version) [large language model]. [find](https://scholar.google.com/scholar?q=OpenAI%2E+2023%2E+Chatgpt+%28mar+23+version%29+%5Blarge+language+model%5D%2E)
23. Lin Pan, Chung-Wei Hang, Haode Qi, Abhishek Shah, Saloni Potdar, and Mo Yu. 2021. Multilingual BERT post-pretraining alignment. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 210–219, Online. As… [find](https://scholar.google.com/scholar?q=Lin+Pan%2C+Chung%2DWei+Hang%2C+Haode+Qi%2C+Abhishek+Shah%2C+Saloni+Potdar%2C+and+Mo+Yu%2E+2021%2E+Multilingual+BERT+post%2Dpretraining+alignment%2E+In+Proceedings+of+the+2021+Conference+of+the+North+American+Chapter+of+t)
24. 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, Brussels, Belgium. Association for Computational Linguistics. https://doi.org/10.18653/v1/W18 -6319 [↗](https://doi.org/10.18653/v1/W18)
25. Rohan Taori, Ishaan Gulrajani, Tianyi Zhang, Yann Dubois, Xuechen Li, Carlos Guestrin, Percy Liang, and Tatsunori B. Hashimoto. 2023. Stanford Alpaca: An instruction-following LLaMA model. [https://github.com/tatsu](https://github.com/tatsu) -lab/stanford alpaca. [↗](https://github.com/tatsu)
26. Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothee Lacroix, Baptiste Roziere, Naman Goyal, Eric Hambro, Faisal Azhar, Aurelien Rodriguez, Armand Joulin, Edouard Grave, and Guillaume Lample. 2023. [LLaMA: Open and efficient foundation language models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-open-efficient-foundation-language/). CoRR, cs…
27. David Vilar, Markus Freitag, Colin Cherry, Jiaming Luo, Viresh Ratnakar, and George Foster. 2023. Prompting PaLM for translation: Assessing strategies and performance. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 15406–1542… [find](https://scholar.google.com/scholar?q=David+Vilar%2C+Markus+Freitag%2C+Colin+Cherry%2C+Jiaming+Luo%2C+Viresh+Ratnakar%2C+and+George+Foster%2E+2023%2E+Prompting+PaLM+for+translation%3A+Assessing+strategies+and+performance%2E+In+Proceedings+of+the+61st+Annua)
28. Ricardo Rei, José G. C. de Souza, Duarte Alves, Chrysoula Zerva, Ana C. Farinha, Taisiya Glushkova, Alon Lavie, Luisa Coheur, and André F. T. Martins. 2022. [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 Proceedings of the Seventh Conference on Machine Translation (WMT), pag…
29. Jason Wei, Maarten Bosma, Vincent Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, Andrew M. Dai, and Quoc V. Le. 2022. Fine-tuned language models are zero-shot learners. In International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Jason+Wei%2C+Maarten+Bosma%2C+Vincent+Zhao%2C+Kelvin+Guu%2C+Adams+Wei+Yu%2C+Brian+Lester%2C+Nan+Du%2C+Andrew+M%2E+Dai%2C+and+Quoc+V%2E+Le%2E+2022%2E+Fine%2Dtuned+language+models+are+zero%2Dshot+learners%2E+In+International+Confere)
30. Jian Yang, Yuwei Yin, Shuming Ma, Haoyang Huang, Dongdong Zhang, Zhoujun Li, and Furu Wei. 2021. Multilingual agreement for multilingual neural machine translation. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference… [find](https://scholar.google.com/scholar?q=Jian+Yang%2C+Yuwei+Yin%2C+Shuming+Ma%2C+Haoyang+Huang%2C+Dongdong+Zhang%2C+Zhoujun+Li%2C+and+Furu+Wei%2E+2021%2E+Multilingual+agreement+for+multilingual+neural+machine+translation%2E+In+Proceedings+of+the+59th+Annual+M)
31. Teven Le Scao, Angela Fan, Christopher Akiki, Ellie Pavlick, Suzana Ilić, Daniel Hesslow, Roman Castagné, Alexandra Sasha Luccioni, François Yvon, Matthias Gallé, et al. 2022. BLOOM: A 176B-parameter open-access multilingual language model. arXiv preprint arXiv:2211.05100v4. [find](https://scholar.google.com/scholar?q=Teven+Le+Scao%2C+Angela+Fan%2C+Christopher+Akiki%2C+Ellie+Pavlick%2C+Suzana+Ilic%CC%81%2C+Daniel+Hesslow%2C+Roman+Castagne%CC%81%2C+Alexandra+Sasha+Luccioni%2C+Franc%CC%A7ois+Yvon%2C+Matthias+Galle%CC%81%2C+et+al%2E+2022%2E+BLOOM%3A+A+176B%2Dparame)
32. Holger Schwenk, Vishrav Chaudhary, Shuo Sun, Hongyu Gong, and Francisco Guzmán. 2021. [WikiMatrix: Mining 135M parallel sentences in 1620 language pairs from Wikipedia](https://md.research.elamur.ai/free/en/papers/zhang-2023-prompting-large-language-model-machine/). In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages…
33. 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…
34. C Comparison of mFTI and Supervised Machine Translation Models Evaluated by COMET We present the comparison of mFTI and supervised MT models evaluated by COMET in Figure 7. It can be seen that when evaluated by COMET, mFTI’s performance is comparable to M2M-1.2B, yet still substantially underperform… [find](https://scholar.google.com/scholar?q=C+Comparison+of+mFTI+and+Supervised+Machine+Translation+Models+Evaluated+by+COMET+We+present+the+comparison+of+mFTI+and+supervised+MT+models+evaluated+by+COMET+in+Figure+7%2E+It+can+be+seen+that+when+ev)
35. Chunting Zhou, Pengfei Liu, Puxin Xu, Srini 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. CoRR, cs.CL/2305.11206v1. [find](https://scholar.google.com/scholar?q=Chunting+Zhou%2C+Pengfei+Liu%2C+Puxin+Xu%2C+Srini+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+Less)
36. D Additional Language Pairs for mFTI Wenhao Zhu, Hongyi Liu, Qingxiu Dong, Jingjing Xu, Lingpeng Kong, Jiajun Chen, Lei Li, and Shujian Huang. 2023. [Multilingual machine translation with large language models: Empirical results and analysis](https://md.research.elamur.ai/free/en/papers/zhu-2024-multilingual-machine-translation-large-language/). CoRR, cs.CL/2304.04675v2.
37. We construct the additional language pairs in Section 4.3 from the other 17 languages covered in the pretraining corpus of XGLM, including Spanish, Greek, Portuguese, Japanese, Vietnamese, Urdu, Thai, Turkish, Telugu, Italian, Haitian, Creole, Basque, Indonesian, Estonian, and Bangali. [find](https://scholar.google.com/scholar?q=We+construct+the+additional+language+pairs+in+Section+4%2E3+from+the+other+17+languages+covered+in+the+pretraining+corpus+of+XGLM%2C+including+Spanish%2C+Greek%2C+Portuguese%2C+Japanese%2C+Vietnamese%2C+Urdu%2C+Thai%2C)

*Updated 24 October 2026*