pith. sign in

arxiv: 2504.01919 · v4 · submitted 2025-04-02 · 💻 cs.CL · cs.AI

Bridging the Linguistic Divide: A Survey on Leveraging Large Language Models for Machine Translation

Baban Gain , Dibyanayan Bandyopadhyay , Asif Ekbal , Trilok Nath Singh This is my paper

Pith reviewed 2026-05-22 21:36 UTC · model grok-4.3

classification 💻 cs.CL cs.AI
keywords large language modelsmachine translationlow-resource translationpreference alignmentsynthetic data generationdocument-level translationreinforcement learning from feedbackmultilingual models
0
0 comments X

The pith

LLM-based machine translation evolves traditional systems by shifting gains toward data quality, preference alignment, and context use rather than model scale.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The survey reviews how large language models apply to machine translation across prompting, fine-tuning, synthetic data, and preference optimization techniques. It examines these methods in low-resource settings, document-level tasks, and evaluation, while highlighting trade-offs in Mixture-of-Experts and multilingual models. The central position is that LLM MT builds on encoder-decoder approaches but now depends more on alignment signals and context handling. A reader would care because this framing points to practical paths for improving translation without endless scaling. The analysis covers strengths and biases in LLM evaluators alongside learned metrics.

Core claim

LLM-based MT is an evolution of traditional MT systems, where gains increasingly depend on data quality, preference alignment, and context utilization rather than scale alone.

What carries the argument

Systematic categorization of methods by data regime, language setting, and technique type, including prompting, parameter-efficient tuning, synthetic data, and RL with human or weak feedback.

If this is right

  • Low-resource translation improves when synthetic data quality, diversity, and preference signals are prioritized over volume.
  • Document-level and discourse-aware MT mostly extends sentence pipelines via context selection, post-editing, or reranking.
  • Mixture-of-Experts and MT-specialized LLMs create explicit trade-offs between scalability and task specialization.
  • LLM evaluators complement but do not replace learned metrics due to their own biases.
  • Open challenges center on robust, inclusive, and controllable systems that work across languages and settings.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Future work could test whether targeted preference optimization on translation pairs yields larger gains than general alignment.
  • The emphasis on context utilization suggests experiments comparing structured discourse features against raw context windows.
  • Trade-offs noted for accessibility may imply that smaller specialized models could match large general ones on specific language pairs.
  • The survey's framing invites direct comparisons of data curation costs versus scaling costs on shared benchmarks.

Load-bearing premise

The selected papers and their groupings represent the full range of LLM MT work without systematic gaps or omitted counterexamples.

What would settle it

Identification of a substantial body of LLM MT research where translation quality improves primarily through increased model scale with no corresponding advances in data quality or preference signals.

read the original abstract

Large Language Models (LLMs) are rapidly reshaping machine translation (MT), particularly by introducing instruction-following, in-context learning, and preference-based alignment into what has traditionally been a supervised encoder-decoder paradigm. This survey provides a comprehensive and up-to-date overview of how LLMs are being leveraged for MT across data regimes, languages, and application settings. We systematically analyze prompting-based methods, parameter-efficient and full fine-tuning strategies, synthetic data generation, preference-based optimization, and reinforcement learning with human and weakly supervised feedback. Special attention is given to low-resource translation, where we examine the roles of synthetic data quality, diversity, and preference signals, as well as the limitations of current RLHF pipelines. We further review recent advances in Mixture-of-Experts models, MT-focused LLMs, and multilingual alignment, highlighting trade-offs between scalability, specialization, and accessibility. Beyond sentence-level translation, we survey emerging document-level and discourse-aware MT methods with LLMs, showing that most approaches extend sentence-level pipelines through structured context selection, post-editing, or reranking rather than requiring fundamentally new data regimes or architectures. Finally, we discuss LLM-based evaluation, its strengths and biases, and its role alongside learned metrics. Overall, this survey positions LLM-based MT as an evolution of traditional MT systems, where gains increasingly depend on data quality, preference alignment, and context utilization rather than scale alone, and outlines open challenges for building robust, inclusive, and controllable translation systems.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 0 minor

Summary. The paper is a survey on leveraging Large Language Models for Machine Translation. It systematically reviews prompting-based methods, parameter-efficient and full fine-tuning, synthetic data generation, preference-based optimization and RL with human/weak feedback, low-resource translation (including synthetic data quality and RLHF limitations), Mixture-of-Experts and MT-focused LLMs, multilingual alignment, document-level and discourse-aware approaches (mostly extending sentence-level pipelines via context selection or post-editing), and LLM-based evaluation. The central positioning is that LLM-based MT evolves traditional systems, with gains now driven more by data quality, preference alignment, and context utilization than by scale alone.

Significance. As a timely synthesis of a fast-moving area, the survey can help researchers navigate trade-offs between scalability, specialization, and accessibility while identifying open challenges for robust and inclusive MT. Its value depends on balanced coverage across the cited regimes and settings.

major comments (1)
  1. [Abstract] Abstract: the positioning that 'gains increasingly depend on data quality, preference alignment, and context utilization rather than scale alone' is the survey's core synthesis claim. To make this load-bearing statement robust, the manuscript should include an explicit synthesis subsection (perhaps in the discussion or conclusion) that aggregates quantitative or comparative evidence from the reviewed works demonstrating diminishing returns to scale versus gains from the other factors.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the thoughtful and constructive comment. We agree that strengthening the core synthesis claim with an explicit subsection will improve the manuscript and will implement the suggested revision.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the positioning that 'gains increasingly depend on data quality, preference alignment, and context utilization rather than scale alone' is the survey's core synthesis claim. To make this load-bearing statement robust, the manuscript should include an explicit synthesis subsection (perhaps in the discussion or conclusion) that aggregates quantitative or comparative evidence from the reviewed works demonstrating diminishing returns to scale versus gains from the other factors.

    Authors: We agree that an explicit synthesis subsection would make the central claim more robust. In the revised manuscript we will add a dedicated subsection (placed in the Discussion) that aggregates comparative evidence from the reviewed literature. This subsection will cite specific studies showing (a) diminishing returns to further scaling in low-resource and domain-specific settings and (b) larger gains obtained from data-quality improvements, preference alignment, and context utilization. Where direct head-to-head comparisons exist in the cited works, we will highlight them; where they are indirect, we will note the limitation while still summarizing the overall pattern observed across the surveyed papers. revision: yes

Circularity Check

0 steps flagged

No significant circularity

full rationale

This is a survey paper with no derivations, equations, fitted parameters, or new empirical claims. The central positioning of LLM-based MT as an evolution of traditional systems is a high-level synthesis of external literature rather than a self-referential derivation. No load-bearing steps reduce to the paper's own inputs by construction, self-citation chains, or ansatz smuggling. The paper is self-contained as a review and carries no circularity burden.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Survey paper; no free parameters, axioms, or invented entities are introduced by the authors.

pith-pipeline@v0.9.0 · 5807 in / 1021 out tokens · 39900 ms · 2026-05-22T21:36:01.141139+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. One Model to Translate Them All? A Journey to Mount Doom for Multilingual Model Merging

    cs.CL 2026-04 unverdicted novelty 7.0

    Merging fine-tuned models for multilingual translation fails because fine-tuning redistributes language-specific neurons rather than sharpening them, increasing representational divergence in output-generating layers.

Reference graph

Works this paper leans on

201 extracted references · 201 canonical work pages · cited by 1 Pith paper · 14 internal anchors

  1. [1]

    In: KOERNER, E.F.K., ASHER, R.E

    Hutchins, W.J.: Machine translation: A brief history. In: KOERNER, E.F.K., ASHER, R.E. (eds.) Concise History of the Language Sciences, pp. 431–445. Pergamon, Amster- dam (1995). https://doi.org/10.1016/B978-0-08-042580-1.50066-0 . https://www.sciencedirect.com/science/article/pii/B9780080425801500660

    work page doi:10.1016/b978-0-08-042580-1.50066-0 1995

  2. [2]

    Computational Linguistics19(2), 263–311 (1993)

    Brown, P.F., Della Pietra, S.A., Della Pietra, V.J., Mercer, R.L.: The mathe- matics of statistical machine translation: Parameter estimation. Computational Linguistics19(2), 263–311 (1993)

    work page 1993

  3. [3]

    Cambridge University Press, ??? (2009)

    Koehn, P.: Statistical Machine Translation. Cambridge University Press, ??? (2009)

    work page 2009

  4. [4]

    Long short -term memory,

    Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput.9(8), 1735–1780 (1997) https://doi.org/10.1162/neco.1997.9.8.1735

    work page doi:10.1162/neco.1997.9.8.1735 1997

  5. [5]

    In: Moschitti, A., Pang, B., Daelemans, W

    Cho, K., Merri¨ enboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., Bengio, Y.: Learning phrase representations using RNN encoder–decoder for statistical machine translation. In: Moschitti, A., Pang, B., Daelemans, W. (eds.) Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1724–1734. Associ...

    work page doi:10.3115/v1/d14-1179 2014

  6. [6]

    In: Proceedings of the 28th International Conference on Neural Infor- mation Processing Systems - Volume 2

    Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Proceedings of the 28th International Conference on Neural Infor- mation Processing Systems - Volume 2. NIPS’14, pp. 3104–3112. MIT Press, Cambridge, MA, USA (2014)

    work page 2014

  7. [7]

    Neural Machine Translation by Jointly Learning to Align and Translate

    Bahdanau, D., Cho, K., Bengio, Y.: Neural Machine Translation by Jointly Learning to Align and Translate (2016). https://arxiv.org/abs/1409.0473

    work page internal anchor Pith review Pith/arXiv arXiv 2016

  8. [8]

    In: M` arquez, L., Callison-Burch, C., Su, 44 J

    Luong, T., Pham, H., Manning, C.D.: Effective approaches to attention- based neural machine translation. In: M` arquez, L., Callison-Burch, C., Su, 44 J. (eds.) Proceedings of the 2015 Conference on Empirical Methods in Nat- ural Language Processing, pp. 1412–1421. Association for Computational Linguistics, Lisbon, Portugal (2015). https://doi.org/10.1865...

    work page doi:10.18653/v1/d15-1166 2015

  9. [9]

    In: Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., Garnett, R

    Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L.u., Polosukhin, I.: Attention is all you need. In: Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 30. Curran Associates, Inc., ??? (2017)

    work page 2017

  10. [10]

    ACM Hum.-Comput

    Zhang, Y., Asamoah Owusu, D., Carpuat, M., Gao, G.: Facilitating global team meetings between language-based subgroups: When and how can machine translation help? Proc. ACM Hum.-Comput. Interact.6(CSCW1) (2022) https: //doi.org/10.1145/3512937

    work page doi:10.1145/3512937 2022

  11. [11]

    In: Su, J., Duh, K., Carreras, X

    Zoph, B., Yuret, D., May, J., Knight, K.: Transfer learning for low-resource neural machine translation. In: Su, J., Duh, K., Carreras, X. (eds.) Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pp. 1568–1575. Association for Computational Linguistics, Austin, Texas (2016). https://doi.org/10.18653/v1/D16-1163 .https...

    work page doi:10.18653/v1/d16-1163 2016

  12. [12]

    In: Walker, M., Ji, H., Stent, A

    Gu, J., Hassan, H., Devlin, J., Li, V.O.K.: Universal neural machine transla- tion for extremely low resource languages. In: Walker, M., Ji, H., Stent, A. (eds.) Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pp. 344–354. Association fo...

    work page doi:10.18653/v1/n18-1032 2018

  13. [13]

    In: Korhonen, A., Traum, D., M` arquez, L

    Kim, Y., Gao, Y., Ney, H.: Effective cross-lingual transfer of neural machine translation models without shared vocabularies. In: Korhonen, A., Traum, D., M` arquez, L. (eds.) Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 1246–1257. Association for Computational Linguistics, Florence, Italy (2019). https://do...

    work page doi:10.18653/v1/p19-1120 2019

  14. [14]

    Proceedings of the AAAI Conference on Artificial Intelligence34(01), 115–122 (2020) https: //doi.org/10.1609/aaai.v34i01.5341

    Ji, B., Zhang, Z., Duan, X., Zhang, M., Chen, B., Luo, W.: Cross-lingual pre- training based transfer for zero-shot neural machine translation. Proceedings of the AAAI Conference on Artificial Intelligence34(01), 115–122 (2020) https: //doi.org/10.1609/aaai.v34i01.5341

    work page doi:10.1609/aaai.v34i01.5341 2020

  15. [15]

    (eds.) Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp

    Aji, A.F., Bogoychev, N., Heafield, K., Sennrich, R.: In neural machine transla- tion, what does transfer learning transfer? In: Jurafsky, D., Chai, J., Schluter, N., Tetreault, J. (eds.) Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 7701–7710. Association for Computational Linguistics, Online (2020). https:/...

    work page doi:10.18653/v1/2020.acl-main.688 2020

  16. [17]

    Data augmentation for low-resource neural machine translation

    Fadaee, M., Bisazza, A., Monz, C.: Data augmentation for low-resource neu- ral machine translation. In: Barzilay, R., Kan, M.-Y. (eds.) Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pp. 567–573. Association for Computational Lin- guistics, Vancouver, Canada (2017). https://doi.org/10.1865...

    work page doi:10.18653/v1/p17-2090 2017

  17. [18]

    Generalized data augmentation for low-resource translation

    Xia, M., Kong, X., Anastasopoulos, A., Neubig, G.: Generalized data augmen- tation for low-resource translation. In: Korhonen, A., Traum, D., M` arquez, L. (eds.) Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 5786–5796. Association for Computational Linguistics, Florence, Italy (2019). https://doi.org/10.1865...

    work page doi:10.18653/v1/p19-1579 2019

  18. [19]

    Ohuoba, A., Sharoff, S., Walker, C.: Quantifying the contribution of MWEs and polysemy in translation errors for English–Igbo MT. In: Scarton, C., Prescott, C., Bayliss, C., Oakley, C., Wright, J., Wrigley, S., Song, X., Gow- Smith, E., Bawden, R., S´ anchez-Cartagena, V.M., Cadwell, P., Lapshinova- Koltunski, E., Cabarr˜ ao, V., Chatzitheodorou, K., Nurm...

    work page 2024

  19. [20]

    In: Al-Onaizan, Y., Bansal, M., Chen, Y.- N

    Yao, B., Jiang, M., Bobinac, T., Yang, D., Hu, J.: Benchmarking machine translation with cultural awareness. In: Al-Onaizan, Y., Bansal, M., Chen, Y.- N. (eds.) Findings of the Association for Computational Linguistics: EMNLP 2024, pp. 13078–13096. Association for Computational Linguistics, Miami, Florida, USA (2024). https://doi.org/10.18653/v1/2024.find...

    work page doi:10.18653/v1/2024.findings-emnlp.765 2024

  20. [21]

    iScience27(10), 110878 (2024) https:// doi.org/10.1016/j.isci.2024.110878

    Naveen, P., Trojovsk´ y, P.: Overview and challenges of machine translation for contextually appropriate translations. iScience27(10), 110878 (2024) https:// doi.org/10.1016/j.isci.2024.110878

    work page doi:10.1016/j.isci.2024.110878 2024

  21. [22]

    In: Rogers, A., Boyd-Graber, J., Okazaki, N

    Dale, D., Voita, E., Barrault, L., Costa-juss` a, M.R.: Detecting and mitigating hallucinations in machine translation: Model internal workings alone do well, sentence similarity Even better. In: Rogers, A., Boyd-Graber, J., Okazaki, N. 46 (eds.) Proceedings of the 61st Annual Meeting of the Association for Com- putational Linguistics (Volume 1: Long Pape...

    work page 2023

  22. [24]

    In: Zong, C., Xia, F., Li, W., Navigli, R

    Zhang, X., Zhang, J., Chen, Z., He, K.: Crafting adversarial examples for neural machine translation. In: Zong, C., Xia, F., Li, W., Navigli, R. (eds.) Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 1967–1977. As...

    work page doi:10.18653/v1/2021.acl-long.153 1967

  23. [25]

    https://arxiv.org/abs/2302

    Sadrizadeh, S., Dolamic, L., Frossard, P.: TransFool: An Adversarial Attack against Neural Machine Translation Models (2023). https://arxiv.org/abs/2302. 00944

    work page 2023

  24. [26]

    In: ICASSP 2023 - 2023 IEEE Inter- national Conference on Acoustics, Speech and Signal Processing (ICASSP), pp

    Sadrizadeh, S., Aghdam, A.D., Dolamic, L., Frossard, P.: Targeted adversarial attacks against neural machine translation. In: ICASSP 2023 - 2023 IEEE Inter- national Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1–5 (2023). https://doi.org/10.1109/ICASSP49357.2023.10095342

    work page doi:10.1109/icassp49357.2023.10095342 2023

  25. [27]

    IEEE Access8, 199523–199538 (2020) https://doi.org/10.1109/ACCESS

    Mohamed, Y.A., Khanan, A., Bashir, M., Mohamed, A.H.H.M., Adiel, M.A.E., Elsadig, M.A.: The impact of artificial intelligence on language translation: A review. IEEE Access12, 25553–25579 (2024) https://doi.org/10.1109/ACCESS. 2024.3366802

    work page doi:10.1109/access 2024

  26. [28]

    In: 2023 10th International Conference on Computing for Sustainable Global Development (INDIACom), pp

    Ul Qumar, S.M., Azim, M., Quadri, S.M.K.: Neural machine translation: A survey of methods used for low resource languages. In: 2023 10th International Conference on Computing for Sustainable Global Development (INDIACom), pp. 1640–1647 (2023)

    work page 2023

  27. [29]

    Cocarascu, F

    Haddow, B., Bawden, R., Miceli Barone, A.V., Helcl, J., Birch, A.: Survey of low- resource machine translation. Computational Linguistics48(3), 673–732 (2022) https://doi.org/10.1162/coli a 00446

    work page doi:10.1162/coli 2022

  28. [30]

    ACM Comput

    Maruf, S., Saleh, F., Haffari, G.: A survey on document-level neural machine translation: Methods and evaluation. ACM Comput. Surv.54(2) (2021) https: //doi.org/10.1145/3441691 47

    work page doi:10.1145/3441691 2021

  29. [31]

    In: Bouamor, H., Pino, J., Bali, K

    Wang, L., Lyu, C., Ji, T., Zhang, Z., Yu, D., Shi, S., Tu, Z.: Document-level machine translation with large language models. In: Bouamor, H., Pino, J., Bali, K. (eds.) Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 16646–16661. Association for Computational Lin- guistics, Singapore (2023). https://doi.org/10.1...

    work page doi:10.18653/v1/2023.emnlp-main.1036 2023

  30. [32]

    https://arxiv.org/ abs/2405.12669

    Shen, H., Shao, L., Li, W., Lan, Z., Liu, Z., Su, J.: A Survey on Multi-modal Machine Translation: Tasks, Methods and Challenges (2024). https://arxiv.org/ abs/2405.12669

    work page arXiv 2024

  31. [33]

    Expert Systems with Applications213, 118993 (2023) https://doi.org/10.1016/j.eswa.2022.118993

    N´ u˜ nez-Marcos, A., Perez-de-Vi˜ naspre, O., Labaka, G.: A survey on sign language machine translation. Expert Systems with Applications213, 118993 (2023) https://doi.org/10.1016/j.eswa.2022.118993

    work page doi:10.1016/j.eswa.2022.118993 2023

  32. [34]

    In: Duh, K., Guzm´ an, F

    Moslem, Y., Haque, R., Kelleher, J., Way, A.: Domain-specific text generation for machine translation. In: Duh, K., Guzm´ an, F. (eds.) Proceedings of the 15th Biennial Conference of the Association for Machine Translation in the Ameri- cas (Volume 1: Research Track), pp. 14–30. Association for Machine Translation in the Americas, Orlando, USA (2022).http...

    work page 2022

  33. [35]

    https://github.com/kingoflolz/mesh-transformer-jax (2021)

    Wang, B., Komatsuzaki, A.: GPT-J-6B: A 6 Billion Parameter Autoregressive Language Model. https://github.com/kingoflolz/mesh-transformer-jax (2021)

    work page 2021

  34. [36]

    Transactions of the Association for Computational Linguistics12, 58–79 (2024) https://doi.org/10

    Shliazhko, O., Fenogenova, A., Tikhonova, M., Kozlova, A., Mikhailov, V., Shavrina, T.: mGPT: Few-shot learners go multilingual. Transactions of the Association for Computational Linguistics12, 58–79 (2024) https://doi.org/10. 1162/tacl a 00633

    work page 2024

  35. [37]

    In: Erk, K., Smith, N.A

    Sennrich, R., Haddow, B., Birch, A.: Improving neural machine translation models with monolingual data. In: Erk, K., Smith, N.A. (eds.) Proceedings of the 54th Annual Meeting of the Association for Computational Linguis- tics (Volume 1: Long Papers), pp. 86–96. Association for Computational Linguistics, Berlin, Germany (2016). https://doi.org/10.18653/v1/...

    work page doi:10.18653/v1/p16-1009 2016

  36. [38]

    doi:10.3115/1073083.1073135 , editor =

    Papineni, K., Roukos, S., Ward, T., Zhu, W.-J.: Bleu: a method for automatic evaluation of machine translation. In: Isabelle, P., Charniak, E., Lin, D. (eds.) Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pp. 311–318. Association for Computational Linguistics, Philadel- phia, Pennsylvania, USA (2002). https://doi...

    work page doi:10.3115/1073083.1073135 2002

  37. [39]

    Post, M.: A call for clarity in reporting BLEU scores. In: Bojar, O., Chatterjee, R., Federmann, C., Fishel, M., Graham, Y., Haddow, B., Huck, M., Yepes, A.J., Koehn, P., Monz, C., Negri, M., N´ ev´ eol, A., Neves, M., Post, M., Specia, L., 48 Turchi, M., Verspoor, K. (eds.) Proceedings of the Third Conference on Machine Translation: Research Papers, pp. ...

    work page doi:10.18653/v1/w18-6319 2018

  38. [40]

    emnlp-main.1173/

    Yin, Y., Zeng, J., Li, Y., Meng, F., Zhang, Y.: LexMatcher: Dictionary-centric data curation for LLM-based machine translation. In: Al-Onaizan, Y., Bansal, M., Chen, Y.-N. (eds.) Findings of the Association for Computational Linguis- tics: EMNLP 2024, pp. 14767–14779. Association for Computational Linguistics, Miami, Florida, USA (2024). https://doi.org/1...

    work page doi:10.18653/v1/2024.findings-emnlp 2024

  39. [41]

    (eds.) Proceedings of the 16th Conference of the Association for Machine Translation in the Americas (Volume 1: Research Track), pp

    Dabre, R., Song, H., Exel, M., Buschbeck, B., Eschbach-Dymanus, J., Tanaka, H.: How effective is synthetic data and instruction fine-tuning for trans- lation with markup using LLMs? In: Knowles, R., Eriguchi, A., Goel, S. (eds.) Proceedings of the 16th Conference of the Association for Machine Translation in the Americas (Volume 1: Research Track), pp. 73...

    work page 2024

  40. [42]

    In: Ojha, A.K., Liu, C.-h., Vylomova, E., Pirinen, F., Abbott, J., Washington, J., Oco, N., Malykh, V., Logacheva, V., Zhao, X

    Frontull, S., Moser, G.: Rule-based, neural and LLM back-translation: Compar- ative insights from a variant of Ladin. In: Ojha, A.K., Liu, C.-h., Vylomova, E., Pirinen, F., Abbott, J., Washington, J., Oco, N., Malykh, V., Logacheva, V., Zhao, X. (eds.) Proceedings of the Seventh Workshop on Technologies for Machine Translation of Low-Resource Languages (L...

    work page doi:10.18653/v1/2024.loresmt-1.13 2024

  41. [43]

    https://arxiv.org/abs/2505.14423

    Gibert, O., Attieh, J., Vahtola, T., Aulamo, M., Li, Z., V´ azquez, R., Hu, T., Tiedemann, J.: Scaling Low-Resource MT via Synthetic Data Generation with LLMs (2025). https://arxiv.org/abs/2505.14423

    work page arXiv 2025

  42. [44]

    No Language Left Behind: Scaling Human-Centered Machine Translation

    Team, N., Costa-juss` a, M.R., Cross, J., C ¸ elebi, O., Elbayad, M., Heafield, K., Heffernan, K., Kalbassi, E., Lam, J., Licht, D., Maillard, J., Sun, A., Wang, S., Wenzek, G., Youngblood, A., Akula, B., Barrault, L., Gonzalez, G.M., Hansanti, P., Hoffman, J., Jarrett, S., Sadagopan, K.R., Rowe, D., Spruit, S., Tran, C., Andrews, P., Ayan, N.F., Bhosale,...

    work page internal anchor Pith review Pith/arXiv arXiv 2022

  43. [45]

    The Llama 3 Herd of Models

    Grattafiori, A., Dubey, A., Jauhri, A., Pandey, A., et al.: The Llama 3 Herd of Models (2024). https://arxiv.org/abs/2407.21783

    work page internal anchor Pith review Pith/arXiv arXiv 2024

  44. [46]

    https://arxiv.org/abs/ 49 2510.11919

    Zebaze, A., Bawden, R., Sagot, B.: LLM Reasoning for Machine Translation: Synthetic Data Generation over Thinking Tokens (2025). https://arxiv.org/abs/ 49 2510.11919

    work page arXiv 2025

  45. [48]

    In: Christodoulopoulos, C., Chakraborty, T., Rose, C., Peng, V

    Gibert, O., Attieh, J., Vahtola, T., Aulamo, M., Li, Z., V´ azquez, R., Hu, T., Tiedemann, J.: Scaling low-resource MT via synthetic data generation with LLMs. In: Christodoulopoulos, C., Chakraborty, T., Rose, C., Peng, V. (eds.) Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pp. 27662–27680. Association for Compu...

    work page doi:10.18653/v1/2025.emnlp-main.1408 2025

  46. [49]

    On the diversity of synthetic data and its impact on training large language models

    Chen, H., Waheed, A., Li, X., Wang, Y., Wang, J., Raj, B., Abdin, M.I.: On the Diversity of Synthetic Data and its Impact on Training Large Language Models (2024). https://arxiv.org/abs/2410.15226

    work page arXiv 2024

  47. [50]

    In: Haddow, B., Kocmi, T., Koehn, P., Monz, C

    Iyer, V., Malik, B., Stepachev, P., Chen, P., Haddow, B., Birch, A.: Quality or quantity? on data scale and diversity in adapting large language models for low- resource translation. In: Haddow, B., Kocmi, T., Koehn, P., Monz, C. (eds.) Pro- ceedings of the Ninth Conference on Machine Translation, pp. 1393–1409. Asso- ciation for Computational Linguistics...

    work page doi:10.18653/v1/2024.wmt-1.128 2024

  48. [51]

    In: Cardoso, H.L., Sousa-Silva, R., Koponen, M., Pareja-Lora, A

    Vajda, D., Vreˇ s, D., ˇSikonja, M.R.: Improving LLMs for machine translation using synthetic preference data. In: Cardoso, H.L., Sousa-Silva, R., Koponen, M., Pareja-Lora, A. (eds.) Proceedings of the 2nd LUHME Workshop, pp. 67–73. UP - Universidade do Porto (https://doi.org/10.21747/978-989-9193-73-4/lan2), LIACC - Laborat´ orio de Inteligˆ encia Artifi...

    work page doi:10.21747/978-989-9193-73-4/lan2 2025

  49. [53]

    https://arxiv.org/abs/2407.02552

    Dang, J., Ahmadian, A., Marchisio, K., Kreutzer, J., ¨Ust¨ un, A., Hooker, S.: RLHF Can Speak Many Languages: Unlocking Multilingual Preference Optimization for LLMs (2024). https://arxiv.org/abs/2407.02552

    work page arXiv 2024

  50. [54]

    White paper, The Asia Foundation and Stanford HAI (2025)

    Pava, J.N., Meinhardt, C., Uz Zaman, H.B., Friedman, T., Truong, S.T., Zhang, 50 D., Cryst, E., Marivate, V., Koyejo, S.: Mind the (language) gap: Mapping the challenges of llm development in low-resource language contexts. White paper, The Asia Foundation and Stanford HAI (2025). https://hai.stanford.edu/assets/ files/hai-taf-pretoria-white-paper-mind-th...

    work page 2025

  51. [55]

    https://openreview.net/forum?id= eDnslTIWSt

    Wang, Y., Bai, A., Peng, N., Hsieh, C.-J.: On the loss of context-awareness in general instruction finetuning (2024). https://openreview.net/forum?id= eDnslTIWSt

    work page 2024

  52. [56]

    Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation

    Wu, Y., Schuster, M., Chen, Z., Le, Q.V., Norouzi, M., Macherey, W., Krikun, M., Cao, Y., Gao, Q., Macherey, K., Klingner, J., Shah, A., Johnson, M., Liu, X., Kaiser, Gouws, S., Kato, Y., Kudo, T., Kazawa, H., Stevens, K., Kurian, G., Patil, N., Wang, W., Young, C., Smith, J., Riesa, J., Rudnick, A., Vinyals, O., Corrado, G., Hughes, M., Dean, J.: Google’...

    work page internal anchor Pith review Pith/arXiv arXiv 2016

  53. [57]

    Jiao, W., Tu, Z., Li, J., Wang, W., Huang, J.-t., Shi, S.: Tencent’s multilin- gual machine translation system for WMT22 large-scale African languages. In: Koehn, P., Barrault, L., Bojar, O., Bougares, F., Chatterjee, R., Costa-juss` a, M.R., Federmann, C., Fishel, M., Fraser, A., Freitag, M., Graham, Y., Grund- kiewicz, R., Guzman, P., Haddow, B., Huck, ...

    work page 2022

  54. [58]

    https://arxiv.org/ abs/2301.08745

    Jiao, W., Wang, W., Huang, J.-t., Wang, X., Shi, S., Tu, Z.: Is ChatGPT A Good Translator? Yes With GPT-4 As The Engine (2023). https://arxiv.org/ abs/2301.08745

    work page arXiv 2023

  55. [59]

    GPT-4 Technical Report

    OpenAI, Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F.L., Almeida, D., Altenschmidt, J., Altman, S., et al.: GPT-4 Technical Report (2024). https://arxiv.org/abs/2303.08774

    work page internal anchor Pith review Pith/arXiv arXiv 2024

  56. [60]

    In: Falk, N., Papi, S., Zhang, M

    Aycock, S., Bawden, R.: Topic-guided example selection for domain adapta- tion in LLM-based machine translation. In: Falk, N., Papi, S., Zhang, M. (eds.) Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop, pp. 175–195. Association for Computational Linguistics, St. Julian’...

    work page 2024

  57. [61]

    IEEE Transactions on Audio, Speech and Language Processing33, 251–261 (2025) https://doi.org/ 10.1109/TASLP.2024.3519814 51

    Ji, B., Duan, X., Zhang, Y., Wu, K., Zhang, M.: Zero-shot prompting for llm- based machine translation using in-domain target sentences. IEEE Transactions on Audio, Speech and Language Processing33, 251–261 (2025) https://doi.org/ 10.1109/TASLP.2024.3519814 51

    work page doi:10.1109/taslp.2024.3519814 2025

  58. [62]

    In: Proceedings of the 6th ACM International Conference on Multimedia in Asia Workshops

    Gao, Y., Wang, R., Hou, F.: How to design translation prompts for chatgpt: An empirical study. In: Proceedings of the 6th ACM International Conference on Multimedia in Asia Workshops. MMAsia ’24 Workshops. Association for Computing Machinery, New York, NY, USA (2024). https://doi.org/10.1145/ 3700410.3702123 .https://doi.org/10.1145/3700410.3702123

    work page doi:10.1145/3700410.3702123 2024

  59. [63]

    In: Proceedings of the 40th International Conference on Machine Learning

    Garcia, X., Bansal, Y., Cherry, C., Foster, G., Krikun, M., Johnson, M., Firat, O.: The unreasonable effectiveness of few-shot learning for machine transla- tion. In: Proceedings of the 40th International Conference on Machine Learning. ICML’23. JMLR.org, ??? (2023)

    work page 2023

  60. [64]

    In: Bouamor, H., Pino, J., Bali, K

    Alves, D., Guerreiro, N., Alves, J., Pombal, J., Rei, R., Souza, J., Colombo, P., Martins, A.: Steering large language models for machine translation with finetun- ing and in-context learning. In: Bouamor, H., Pino, J., Bali, K. (eds.) Findings of the Association for Computational Linguistics: EMNLP 2023, pp. 11127–11148. Association for Computational Lin...

    work page doi:10.18653/v1/2023.findings-emnlp.744 2023

  61. [65]

    Bawden, R., Yvon, F.: Investigating the translation performance of a large multilingual language model: the case of BLOOM. In: Nurminen, M., Bren- ner, J., Koponen, M., Latomaa, S., Mikhailov, M., Schierl, F., Ranasinghe, T., Vanmassenhove, E., Vidal, S.A., Aranberri, N., Nunziatini, M., Escart´ ın, C.P., Forcada, M., Popovic, M., Scarton, C., Moniz, H. (...

    work page 2023

  62. [66]

    https://arxiv.org/abs/2302

    Hendy, A., Abdelrehim, M., Sharaf, A., Raunak, V., Gabr, M., Matsushita, H., Kim, Y.J., Afify, M., Awadalla, H.H.: How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation (2023). https://arxiv.org/abs/2302. 09210

    work page 2023

  63. [68]

    In: Rogers, A., Boyd-Graber, J., Okazaki, N

    Vilar, D., Freitag, M., Cherry, C., Luo, J., Ratnakar, V., Foster, G.: Prompting PaLM for translation: Assessing strategies and performance. In: Rogers, A., Boyd-Graber, J., Okazaki, N. (eds.) Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 15406–15427. Association for Computational Ling...

    work page doi:10.18653/v1/2023.acl-long.859 2023

  64. [69]

    In: Proceedings of the 40th International Conference on Machine Learning

    Zhang, B., Haddow, B., Birch, A.: Prompting large language model for machine translation: a case study. In: Proceedings of the 40th International Conference on Machine Learning. ICML’23. JMLR.org, ??? (2023)

    work page 2023

  65. [70]

    GLM, T., Zeng, A., Xu, B., Wang, B., Zhang, C., et al.: ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools (2024)

    work page 2024

  66. [71]

    https://arxiv

    Tang, L., Qin, J., Ye, W., Tan, H., Yang, Z.: Adaptive Few-shot Prompting for Machine Translation with Pre-trained Language Models (2025). https://arxiv. org/abs/2501.01679

    work page arXiv 2025

  67. [72]

    In: Rogers, A., Boyd-Graber, J., Okazaki, N

    Agrawal, S., Zhou, C., Lewis, M., Zettlemoyer, L., Ghazvininejad, M.: In- context examples selection for machine translation. In: Rogers, A., Boyd-Graber, J., Okazaki, N. (eds.) Findings of the Association for Computational Linguis- tics: ACL 2023, pp. 8857–8873. Association for Computational Linguistics, Toronto, Canada (2023). https://doi.org/10.18653/v...

    work page doi:10.18653/v1/2023.findings-acl.564 2023

  68. [73]

    Yifan Li, Yifan Du, Kun Zhou, Jinpeng Wang, Xin Zhao, and Ji-Rong Wen

    Kumar, A., Puduppully, R., Dabre, R., Kunchukuttan, A.: CTQScorer: Combin- ing multiple features for in-context example selection for machine translation. In: Bouamor, H., Pino, J., Bali, K. (eds.) Findings of the Association for Computational Linguistics: EMNLP 2023, pp. 7736–7752. Association for Com- putational Linguistics, Singapore (2023). https://do...

    work page doi:10.18653/v1/2023 2023

  69. [74]

    In: Utiyama, M., Wang, R

    Sia, S., Duh, K.: In-context learning as maintaining coherency: A study of on- the-fly machine translation using large language models. In: Utiyama, M., Wang, R. (eds.) Proceedings of Machine Translation Summit XIX, Vol. 1: Research Track, pp. 173–185. Asia-Pacific Association for Machine Translation, Macau SAR, China (2023).https://aclanthology.org/2023....

    work page 2023

  70. [75]

    In: Calzolari, N., Kan, M.-Y., Hoste, V., Lenci, A., Sakti, S., Xue, N

    Ji, B., Duan, X., Qiu, Z., Zhang, T., Li, J., Yang, H., Zhang, M.: Submodular- based in-context example selection for LLMs-based machine translation. In: Calzolari, N., Kan, M.-Y., Hoste, V., Lenci, A., Sakti, S., Xue, N. (eds.) Proceed- ings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-C...

    work page 2024

  71. [76]

    https://arxiv.org/ abs/2408.00397 53

    Zebaze, A., Sagot, B., Bawden, R.: In-Context Example Selection via Similarity Search Improves Low-Resource Machine Translation (2024). https://arxiv.org/ abs/2408.00397 53

    work page arXiv 2024

  72. [77]

    In: Duh, K., Gomez, H., Bethard, S

    Zhu, W., Liu, H., Dong, Q., Xu, J., Huang, S., Kong, L., Chen, J., Li, L.: Multilin- gual machine translation with large language models: Empirical results and anal- ysis. In: Duh, K., Gomez, H., Bethard, S. (eds.) Findings of the Association for Computational Linguistics: NAACL 2024, pp. 2765–2781. Association for Com- putational Linguistics, Mexico City...

    work page 2024

  73. [78]

    https://arxiv.org/abs/2505.22293

    Frontull, S., Str¨ ohle, T.: Compensating for Data with Reasoning: Low-Resource Machine Translation with LLMs (2025). https://arxiv.org/abs/2505.22293

    work page arXiv 2025

  74. [79]

    In: Text Summarization Branches Out, pp

    Lin, C.-Y.: ROUGE: A package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74–81. Association for Computational Linguistics, Barcelona, Spain (2004).https://aclanthology.org/W04-1013/

    work page 2004

  75. [80]

    In: Bojar, O., Chatterjee, R., Federmann, C., Haddow, B., Hokamp, C., Huck, M., Logacheva, V., Pecina, P

    Popovi´ c, M.: chrF: character n-gram F-score for automatic MT evaluation. In: Bojar, O., Chatterjee, R., Federmann, C., Haddow, B., Hokamp, C., Huck, M., Logacheva, V., Pecina, P. (eds.) Proceedings of the Tenth Workshop on Statistical Machine Translation, pp. 392–395. Association for Computational Linguistics, Lisbon, Portugal (2015). https://doi.org/10...

    work page doi:10.18653/v1/w15-3049 2015

  76. [81]

    In: Webber, B., Cohn, T., He, Y., Liu, Y

    Rei, R., Stewart, C., Farinha, A.C., Lavie, A.: COMET: A neural frame- work for MT evaluation. In: Webber, B., Cohn, T., He, Y., Liu, Y. (eds.) Proceedings of the 2020 Conference on Empirical Methods in Natural Lan- guage Processing (EMNLP), pp. 2685–2702. Association for Computational Linguistics, Online (2020). https://doi.org/10.18653/v1/2020.emnlp-mai...

    work page doi:10.18653/v1/2020.emnlp-main.213 2020

  77. [82]

    In: Bouamor, H., Pino, J., Bali, K

    Peng, K., Ding, L., Zhong, Q., Shen, L., Liu, X., Zhang, M., Ouyang, Y., Tao, D.: Towards making the most of ChatGPT for machine translation. In: Bouamor, H., Pino, J., Bali, K. (eds.) Findings of the Association for Computational Lin- guistics: EMNLP 2023, pp. 5622–5633. Association for Computational Linguis- tics, Singapore (2023). https://doi.org/10.18...

    work page doi:10.18653/v1/2023.findings-emnlp.373 2023

  78. [84]

    In: Bouamor, H., Pino, J., Bali, K

    Puduppully, R., Kunchukuttan, A., Dabre, R., Aw, A.T., Chen, N.: DecoMT: Decomposed prompting for machine translation between related languages using large language models. In: Bouamor, H., Pino, J., Bali, K. (eds.) 54 Proceedings of the 2023 Conference on Empirical Methods in Natural Lan- guage Processing, pp. 4586–4602. Association for Computational Lin...

    work page doi:10.18653/v1/2023.emnlp-main.279 2023

  79. [85]

    Chen, P., Guo, Z., Haddow, B., Heafield, K.: Iterative translation refine- ment with large language models. In: Scarton, C., Prescott, C., Bayliss, C., Oakley, C., Wright, J., Wrigley, S., Song, X., Gow-Smith, E., Bawden, R., S´ anchez-Cartagena, V.M., Cadwell, P., Lapshinova-Koltunski, E., Cabarr˜ ao, V., Chatzitheodorou, K., Nurminen, M., Kanojia, D., M...

    work page 2024

  80. [87]

    In: Chiruzzo, L., Ritter, A., Wang, L

    Feng, Z., Zhang, Y., Li, H., Wu, B., Liao, J., Liu, W., Lang, J., Feng, Y., Wu, J., Liu, Z.: TEaR: Improving LLM-based machine translation with system- atic self-refinement. In: Chiruzzo, L., Ritter, A., Wang, L. (eds.) Findings of the Association for Computational Linguistics: NAACL 2025, pp. 3922–3938. Association for Computational Linguistics, Albuquer...

    work page 2025

Showing first 80 references.