Elamur Research⌕
☰
home / papers / 2026 / Why do Large Language Models Fail in Low-resource Translation? Unraveling the Token Dynamics of Large Language Models for Machine Translation

Why do Large Language Models Fail in Low-resource Translation? Unraveling the Token Dynamics of Large Language Models for Machine Translation

Summary

LLMs translate well overall, yet little research explains why their output degrades for low-resource and non-English-centric language pairs. Qian and Scherrer study this by running 15 systems on 22 language pairs of differing resource levels and scoring the outputs with COMET-22 and SacreBLEU. The systems include instruction-tuned and reasoning LLMs from the Qwen, DeepSeek, Llama, Gemma, Aya and Tower families, plus NLLB baselines and Google Translate. To keep automatic scores reliable, the authors compared three prompt templates and kept the one that produced the least extraneous text.

Their central tool is a new measure, Token Activation Rate (TAR). It estimates how much of a model's language-specific vocabulary is actually used during generation. They validate it against models whose training-language mix is documented.

Pairs without English score consistently worse. Low TAR and large typological distance both go together with weaker quality. Reasoning models generate more tokens when the target language has low TAR, which suggests compensation, but whether this improves quality depends on the model. The study positions token-level behaviour as a diagnostic lens for multilingual LLM failures.

Key points

  • The test set covers 10 non-English-centric pairs (e.g., ar-zh, ko-fr, de-it) and 12 English-centric pairs (6 en-XX, 6 XX-en). It draws on the TED Multilingual Parallel Corpora, SwissAdmin, a Chinese-Korean parallel corpus and the WMT20 Quality Estimation data, with 3,000 sampled sentences per pair (66,000 in total).
  • Four of the 15 models are reasoning LLMs: Qwen3-30B-A3B-Thinking-2507, Qwen3-4B-Thinking-2507, DeepSeek-R1-Distill-Qwen-32B and the DeepSeek-V3.2-Exp reasoner. Supplementary analyses add K2-Think-V2 and Olmo-3-7B-Think.
  • Target-language TAR correlates negatively with the average number of reasoning tokens (Pearson r = −0.3045, Spearman ρ = −0.4917, Kendall τ = −0.3414), and all three correlations are statistically significant.
  • The link between extra reasoning tokens and COMET/BLEU gains varies by model. It is positive for Qwen3-4B-Thinking-2507 but weak or negative for DeepSeek-V3.2-Exp-671B-reasoner and K2-Think-V2. Explanatory noise in outputs (e.g., from gemma-3-27b-it) can also distort the scores.
  • The code is released at github.com/shenbinqian/llm4mt. The experiments took about 200 GPU hours (≈397.64 kWh) on Norway's Olivia supercomputer. The authors note that their findings are correlational, not causal.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

Fields: Linguistics & languages · Machine translation

Topics: Machine translation

Cite

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

@inproceedings{qian2026why,
  title = {{Why do Large Language Models Fail in Low-resource Translation? Unraveling the Token Dynamics of Large Language Models for Machine Translation}},
  author = {Qian, Shenbin and Scherrer, Yves},
  booktitle = {Proceedings of the 26th Annual Conference of the European Association for Machine Translation (Volume 1)},
  year = {2026},
  url = {https://aclanthology.org/2026.eamt-1.4/}
}

References

69 references, 27 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Ahn, Janice, Rishu Verma, Renze Lou, Di Liu, Rui Zhang, and Wenpeng Yin. 2024. Large language models for mathematical reasoning: Progresses and challenges. In Falk, Neele, Sara Papi, and Mike Zhang, editors, Proceedings of the 18th Conference of the European Chapter of the Association for Computatio… find our card
  2. Apertus Project, Alejandro Hernández-Cano, Alexander Hägele, Allen Hao Huang, Angelika Romanou, Antoni-Joan Solergibert, Barna Pasztor, Bettina Messmer, Dhia Garbaya, Eduard Frank Ďurech, Ido Hakimi, Juan García Giraldo, Mete Ismayilzada, Negar Foroutan, Skander Moalla, Tiancheng Chen, Vinko Sabolc… find
  3. Barrault, Loïc, Magdalena Biesialska, Ondřej Bojar, Marta R. Costa-jussà, Christian Federmann, Yvette Graham, Roman Grundkiewicz, Barry Haddow, Matthias Huck, Eric Joanis, Tom Kocmi, Philipp Koehn, Chi-kiu Lo, Nikola Ljubešić, Christof Monz, Makoto Morishita, Masaaki Nagata, Toshiaki Nakazawa, San… find our card
  4. BigScience Workshop, Teven Le Scao, Angela Fan, Christopher Akiki, Ellie Pavlick, Suzana Ilić, Daniel Hesslow, Roman Castagné, Alexandra Sasha Luccioni, François Yvon, Matthias Gallé, Jonathan Tow, Alexander M Rush, Stella Biderman, Albert Webson, Pawan Sasanka Ammanamanchi, Thomas Wang, Benoît Sag… find
  5. Bojanowski, Piotr, Edouard Grave, Armand Joulin, and Tomas Mikolov. 2017. Enriching word vectors with subword information. Transactions of the Association for Computational Linguistics, 5:135–146. find
  6. Castaldo, Antonio and Johanna Monti. 2024. Prompting large language models for idiomatic translation. In Vanroy, Bram, Marie-Aude Lefer, Lieve Macken, and Paola Ruffo, editors, Proceedings of the 1st Workshop on Creative-text Translation and Technology, pages 32–39, Sheffield, United Kingdom, June.… find
  7. Caswell, Isaac. 2024. 110 new languages are coming to Google Translate. Accessed on 10, Dec 2025. find
  8. Chizhov, Pavel, Catherine Arnett, Elizaveta Korotkova, and Ivan P. Yamshchikov. 2024. BPE gets picky: Efficient vocabulary refinement during tokenizer training. In Al-Onaizan, Yaser, Mohit Bansal, and Yun-Nung Chen, editors, Proceedings of the 2024 Conference on Empirical Methods in Natural Language… find
  9. Court, Sara and Micha Elsner. 2024. Shortcomings of LLMs for low-resource translation: Retrieval and understanding are both the problem. In Haddow, Barry, Tom Kocmi, Philipp Koehn, and Christof Monz, editors, Proceedings of the Ninth Conference on Machine Translation, pages 1332–1354, Miami, Florida… find
  10. Dang, John, 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… find our card
  11. DeepSeek-AI. 2025. Deepseek-v3.2-exp: Boosting long-context efficiency with deepseek sparse attention. Accessed on 08, Dec 2025. find
  12. Gemma Team, Aishwarya Kamath, Johan Ferret, Shreya Pathak, Nino Vieillard, Ramona Merhej, Sarah Perrin, Tatiana Matejovicova, Alexandre Ramé, Morgane Rivière, Louis Rouillard, Thomas Mesnard, Geoffrey Cideron, Jean-Bastien Grill, Sabela Ramos, Edouard Yvinec, Michelle Casbon, Etienne Pot, Ivo Penche… find
  13. Groeneveld, Dirk, Iz Beltagy, Evan Walsh, Akshita Bhagia, Rodney Kinney, Oyvind Tafjord, Ananya Jha, Hamish Ivison, Ian Magnusson, Yizhong Wang, Shane Arora, David Atkinson, Russell Authur, Khyathi Chandu, Arman Cohan, Jennifer Dumas, Yanai Elazar, Yuling Gu, Jack Hessel, Tushar Khot, William Merril… find
  14. Guo, Daya, Dejian Yang, Haowei Zhang, Junxiao Song, Peiyi Wang, Qihao Zhu, Runxin Xu, Ruoyu Zhang, Shirong Ma, Xiao Bi, Xiaokang Zhang, Xingkai Yu, Yu Wu, Z F Wu, Zhibin Gou, Zhihong Shao, Zhuoshu Li, Ziyi Gao, Aixin Liu, Bing Xue, Bingxuan Wang, Bochao Wu, Bei Feng, Chengda Lu, Chenggang Zhao, Chen… find
  15. Guzmán, Francisco, Peng-Jen Chen, Myle Ott, Juan Pino, Guillaume Lample, Philipp Koehn, Vishrav Chaudhary, and Marc’Aurelio Ranzato. 2019. The FLORES evaluation datasets for low-resource machine translation: Nepali–English and Sinhala– English. In Inui, Kentaro, Jing Jiang, Vincent Ng, and Xiaojun W… find our card
  16. He, Sui. 2024. Prompting ChatGPT for translation: A comparative analysis of translation brief and persona prompts. In Scarton, Carolina, Charlotte Prescott, Chris Bayliss, Chris Oakley, Joanna Wright, Stuart Wrigley, Xingyi Song, Edward Gow-Smith, Rachel Bawden, Víctor M Sánchez-Cartagena, Patrick C… find
  17. Hendrycks, Dan, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. 2021. Measuring Massive Multitask Language Understanding. In International Conference on Learning Representations. find our card
  18. Hinton, Geoffrey, Oriol Vinyals, and Jeff Dean. 2015. Distilling the knowledge in a neural network. arXiv preprint, March. find our card
  19. Hirak, Vitalii, Jaap Jumelet, and Arianna Bisazza. 2026. Assessing the Impact of Typological Features on Multilingual Machine Translation in the Age of Large Language Models. In Demberg, Vera, Kentaro Inui, and Lluís Marquez, editors, Proceedings of the 19th Conference of the European Chapter of the… find
  20. Huang, Xu, Wenhao Zhu, Hanxu Hu, Conghui He, Lei Li, Shujian Huang, and Fei Yuan. 2025. BenchMAX: A comprehensive multilingual evaluation suite for large language models. In Christodoulopoulos, Christos, Tanmoy Chakraborty, Carolyn Rose, and Violet Peng, editors, Findings of the Association for Comp… find
  21. Jiang, Juyong, Fan Wang, Jiasi Shen, Sungju Kim, and Sunghun Kim. 2025. A survey on large language models for code generation. ACM Trans. Softw. Eng. Methodol., July. Just Accepted. find our card
  22. K2 Team, Zhengzhong Liu, Liping Tang, Linghao Jin, Haonan Li, Nikhil Ranjan, Desai Fan, Shaurya Rohatgi, Richard Fan, Omkar Pangarkar, Huijuan Wang, Zhoujun Cheng, Suqi Sun, Seungwook Han, Bowen Tan, Gurpreet Gosal, Xudong Han, Varad Pimpalkhute, Shibo Hao, Ming Shan Hee, Joel Hestness, Haolong Jia,… find
  23. Khiu, Eric, Hasti Toossi, David Anugraha, Jinyu Liu, Jiaxu Li, Juan Flores, Leandro Roman, A. Seza Doğruöz, and En-Shiun Lee. 2024. Predicting machine translation performance on low-resource languages: The role of domain similarity. In Graham, Yvette and Matthew Purver, editors, Findings of the Ass… find
  24. Kocmi, Tom, Eleftherios Avramidis, Rachel Bawden, Ondřej Bojar, Anton Dvorkovich, Christian Federmann, Mark Fishel, Markus Freitag, Thamme Gowda, Roman Grundkiewicz, Barry Haddow, Marzena Karpinska, Philipp Koehn, Benjamin Marie, Christof Monz, Kenton Murray, Masaaki Nagata, Martin Popel, Maja Popo… find our card
  25. Kulkarni, Ajinkya. 2015. TED Multilingual Parallel Corpus. GitHub, 12. Accessed on 08, Dec 2025. find
  26. Kwon, Woosuk, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph Gonzalez, Hao Zhang, and Ion Stoica. 2023. Efficient memory management for large language model serving with pagedattention. In Proceedings of the 29th Symposium on Operating Systems Principles, SOSP ’23, page 61… find
  27. Lambert, Nathan, Jacob Morrison, Valentina Pyatkin, Shengyi Huang, Hamish Ivison, Faeze Brahman, Lester James V Miranda, Alisa Liu, Nouha Dziri, Shane Lyu, Yuling Gu, Saumya Malik, Victoria Graf, Jena D Hwang, Jiangjiang Yang, Ronan Le Bras, Oyvind Tafjord, Chris Wilhelm, Luca Soldaini, Noah A Smith… find our card
  28. Lannelongue, Loïc, Jason Grealey, and Michael Inouye. 2021. Green algorithms: Quantifying the carbon footprint of computation. Advanced Science, 8(12):2100707. find
  29. Littell, Patrick, David R. Mortensen, Ke Lin, Katherine Kairis, Carlisle Turner, and Lori Levin. 2017. URIEL and lang2vec: Representing languages as typological, geographical, and phylogenetic vectors. In Lapata, Mirella, Phil Blunsom, and Alexander Koller, editors, Proceedings of the 15th Conferenc… find our card
  30. Liu, Sinuo, Chenyang Lyu, Minghao Wu, Longyue Wang, Weihua Luo, Kaifu Zhang, and Zifu Shang. 2025. New trends for modern machine translation with large reasoning models. arXiv preprint, March. find our card
  31. Lundin, Jessica M, Ada Zhang, Nihal Karim, Hamza Louzan, Victor Wei, David Adelani, and Cody Carroll. 2025. The token tax: Systematic bias in multilingual tokenization. arXiv preprint, September. find
  32. Martins, Pedro Henrique, Patrick Fernandes, João Alves, Nuno M Guerreiro, Ricardo Rei, Duarte M Alves, José Pombal, Amin Farajian, Manuel Faysse, Mateusz Klimaszewski, Pierre Colombo, Barry Haddow, José G C de Souza, Alexandra Birch, and André F T Martins. 2024. EuroLLM: Multilingual language models… find our card
  33. Meta AI. 2024. Llama 3.2: Revolutionizing edge AI and vision with open, customizable models. Accessed on 08, Dec 2025. find
  34. NLLB Team, 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 Hoff… find
  35. Olmo Team, Allyson Ettinger, Amanda Bertsch, Bailey Kuehl, David Graham, David Heineman, Dirk Groeneveld, Faeze Brahman, Finbarr Timbers, Hamish Ivison, Jacob Morrison, Jake Poznanski, Kyle Lo, Luca Soldaini, Matt Jordan, Mayee Chen, Michael Noukhovitch, Nathan Lambert, Pete Walsh, Pradeep Dasigi, R… find our card
  36. OpenAI, Aaron Jaech, Adam Kalai, Adam Lerer, Adam Richardson, Ahmed El-Kishky, Aiden Low, Alec Helyar, Aleksander Madry, Alex Beutel, Alex Carney, Alex Iftimie, Alex Karpenko, Alex Tachard Passos, Alexander Neitz, Alexander Prokofiev, Alexander Wei, Allison Tam, Ally Bennett, Ananya Kumar, Andre Sar… find our card
  37. OpenAI. 2024. Introducing SWE-bench Verified. Accessed on 11, Dec 2025. find
  38. Papineni, Kishore, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In Isabelle, Pierre, Eugene Charniak, and Dekang Lin, editors, Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pages 311–318, P… find our card
  39. Park, Jeonghyeok and Hai Zhao. 2019. Korean-to-Chinese Machine Translation using Chinese Character as Pivot Clue. arXiv preprint, November. find
  40. Phan, Long, Alice Gatti, Ziwen Han, Nathaniel Li, Josephina Hu, Hugh Zhang, Chen Bo Calvin Zhang, Mohamed Shaaban, John Ling, Sean Shi, Michael Choi, Anish Agrawal, Arnav Chopra, Adam Khoja, Ryan Kim, Richard Ren, Jason Hausenloy, Oliver Zhang, Mantas Mazeika, Dmitry Dodonov, Tung Nguyen, Jaeho Lee,… find our card
  41. Ploeger, Esther, Johannes Bjerva, Jörg Tiedemann, and Robert Oestling. 2025. A cross-lingual perspective on neural machine translation difficulty. In Haddow, Barry, Tom Kocmi, Philipp Koehn, and Christof Monz, editors, Proceedings of the Tenth Conference on Machine Translation, pages 340–354, Suzhou… find
  42. Popović, Maja. 2017. chrF++: words helping character n-grams. In Bojar, Ondřej, Christian Buck, Rajen Chatterjee, Christian Federmann, Yvette Graham, Barry Haddow, Matthias Huck, Antonio Jimeno Yepes, Philipp Koehn, and Julia Kreutzer, editors, Proceedings of the Second Conference on Machine Trans… find our card
  43. Post, Matt. 2018. A call for clarity in reporting BLEU scores. In Bojar, Ondřej, Rajen Chatterjee, Christian Federmann, Mark Fishel, Yvette Graham, Barry Haddow, Matthias Huck, Antonio Jimeno Yepes, Philipp Koehn, Christof Monz, Matteo Negri, Aurélie Névéol, Mariana Neves, Matt Post, Lucia Specia,… find our card
  44. Provilkov, Ivan, Dmitrii Emelianenko, and Elena Voita. 2020. BPE-dropout: Simple and effective subword regularization. In Jurafsky, Dan, Joyce Chai, Natalie Schluter, and Joel Tetreault, editors, Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1882–1892… find our card
  45. Pu, Xiao, Mingqi Gao, and Xiaojun Wan. 2023. Summarization is (almost) dead. arXiv preprint, September. find
  46. Qwen Team. 2024. Qwen2.5: A Party of Foundation Models!, 9. Accessed on 08, Dec 2025. find
  47. Qwen Team. 2025. Qwen3: Think Deeper, Act Faster, 4. Accessed on 08, Dec 2025. find
  48. Rei, Ricardo, Craig Stewart, Ana C Farinha, and Alon Lavie. 2020. COMET: A neural framework for MT evaluation. In Webber, Bonnie, Trevor Cohn, Yulan He, and Yang Liu, editors, Proceedings of the 2020 find our card
  49. Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 2685–2702, Online, November. Association for Computational Linguistics. find
  50. Rei, Ricardo, José G. C. de Souza, Duarte Alves, Chrysoula Zerva, Ana C Farinha, Taisiya Glushkova, Alon Lavie, Luisa Coheur, and André F. T. Martins. 2022a. COMET-22: Unbabel-IST 2022 submission for the metrics shared task. In Koehn, Philipp, Loïc Barrault, Ondřej Bojar, Fethi Bougares, Rajen Chat… find our card
  51. Rei, Ricardo, Marcos Treviso, Nuno M. Guerreiro, Chrysoula Zerva, Ana C Farinha, Christine Maroti, José G. C. de Souza, Taisiya Glushkova, Duarte Alves, Luisa Coheur, Alon Lavie, and André F. T. Martins. 2022b. find
  52. CometKiwi: IST-unbabel 2022 submission for the quality estimation shared task. In Koehn, Philipp, Loïc Barrault, Ondřej Bojar, Fethi Bougares, Rajen Chatterjee, Marta R. Costa-jussà, Christian Federmann, Mark Fishel, Alexander Fraser, Markus Freitag, Yvette Graham, Roman Grundkiewicz, Paco Guzman,… find our card
  53. Rei, Ricardo, Nuno M Guerreiro, José Pombal, João Alves, Pedro Teixeirinha, Amin Farajian, and André F T Martins. 2025. Tower+: Bridging generality and translation specialization in multilingual LLMs. arXiv preprint, June. find
  54. Romanou, Angelika, Negar Foroutan, Anna Sotnikova, Sree Harsha Nelaturu, Shivalika Singh, Rishabh Maheshwary, Micol Altomare, Zeming Chen, Mohamed A. Haggag, Snegha A, Alfonso Amayuelas, Azril Hafizi Amirudin, Danylo Boiko, Michael Chang, Jenny Chim, Gal Cohen, Aditya Kumar Dalmia, Abraham Diress, S… find
  55. Rust, Phillip, Jonas Pfeiffer, Ivan Vulić, Sebastian Ruder, and Iryna Gurevych. 2021. How good is your tokenizer? on the monolingual performance of multilingual language models. In Zong, Chengqing, Fei Xia, Wenjie Li, and Roberto Navigli, editors, Proceedings of the 59th Annual Meeting of the Assoc… find our card
  56. Scherrer, Yves, Luka Nerima, Lorenza Russo, Maria Ivanova, and Eric Wehrli. 2014. SwissAdmin: A multilingual tagged parallel corpus of press releases. In Calzolari, Nicoletta, Khalid Choukri, Thierry Declerck, Hrafn Loftsson, Bente Maegaard, Joseph Mariani, Asuncion Moreno, Jan Odijk, and Stelios Pi… find
  57. Schwartz, Roy, Jesse Dodge, Noah A. Smith, and Oren Etzioni. 2020. Green ai. Commun. ACM, 63(12):54–63, November. find our card
  58. Sindhujan, Archchana, Diptesh Kanojia, Constantin Orasan, and Shenbin Qian. 2025. When LLMs struggle: Reference-less translation evaluation for low-resource languages. In Hettiarachchi, Hansi, Tharindu Ranasinghe, Paul Rayson, Ruslan Mitkov, Mohamed Gaber, Damith Premasiri, Fiona Anting Tan, and Las… find
  59. Singh, Telem Joyson, Ranbir Singh Sanasam, and Priyankoo Sarmah. 2025. An information-theoretic approach to reducing fertility in LLMs for Manipuri machine translation. In Inui, Kentaro, Sakriani Sakti, Haofen Wang, Derek F. Wong, Pushpak Bhattacharyya, Biplab Banerjee, Asif Ekbal, Tanmoy Chakrabort… find
  60. Song, Yewei, Lujun Li, Cedric Lothritz, Saad Ezzini, Lama Sleem, Niccolo Gentile, Radu State, Tegawendé F Bissyandé, and Jacques Klein. 2025. Is small language model the silver bullet to low-resource languages machine translation? arXiv preprint, August. find
  61. Stewart, Craig, Ricardo Rei, Catarina Farinha, and Alon Lavie. 2020. COMET - deploying a new state-of-the-art MT evaluation metric in production. In Campbell, Janice, Dmitriy Genzel, Ben Huyck, and Patricia O’Neill-Brown, editors, Proceedings of the 14th Conference of the Association for Machine Tra… find
  62. Vilar, David, Markus Freitag, Colin Cherry, Jiaming Luo, Viresh Ratnakar, and George Foster. 2023. Prompting PaLM for translation: Assessing strategies and performance. In Rogers, Anna, Jordan Boyd-Graber, and Naoaki Okazaki, editors, Proceedings of the 61st Annual Meeting of the Association for Com… find
  63. Wang, Alex, Yada Pruksachatkun, Nikita Nangia, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel R. Bowman. 2019. Super-GLUE: a stickier benchmark for general-purpose language understanding systems. In Proceedings of the 33rd International Conference on Neural Information Processing… find
  64. Wolf, Thomas, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pier-ric Cistac, Tim Rault, Remi Louf, Morgan Funtowicz, Joe Davison, Sam Shleifer, Patrick von Platen, Clara Ma, Yacine Jernite, Julien Plu, Canwen Xu, Teven Le Scao, Sylvain Gugger, Mariama Drame, Quentin Lh… find our card
  65. Ye, Yongshi, Biao Fu, Chongxuan Huang, Yidong Chen, and Xiaodong Shi. 2025. How well do large reasoning models translate? a comprehensive evaluation for multi-domain machine translation. arXiv preprint, May. find
  66. Yue, Xiang, Tianyu Zheng, Yuansheng Ni, Yubo Wang, Kai Zhang, Shengbang Tong, Yuxuan Sun, Botao Yu, Ge Zhang, Huan Sun, Yu Su, Wenhu Chen, and Graham Neubig. 2025. MMMU-pro: A more robust multi-discipline multimodal understanding benchmark. In Che, Wanxiang, Joyce Nabende, Ekaterina Shutova, and Moh… find
  67. Zhang, Biao, Barry Haddow, and Alexandra Birch. 2023. Prompting large language model for machine translation: a case study. In Proceedings of the 40th International Conference on Machine Learning, ICML’23. JMLR.org. find our card
  68. Zhang, Wenxuan, Yue Deng, Bing Liu, Sinno Pan, and Lidong Bing. 2024. Sentiment analysis in the era of large language models: A reality check. In Duh, Kevin, Helena Gomez, and Steven Bethard, editors, Findings of the Association for Computational Linguistics: NAACL 2024, pages 3881–3906, Mexico City… find our card
  69. Zhang, Biao, Fedor Moiseev, Joshua Ainslie, Paul Suganthan, Min Ma, Surya Bhupatiraju, Fede Lebron, Orhan Firat, Armand Joulin, and Zhe Dong. 2025. Encoder-decoder Gemma: Improving the quality-efficiency trade-off via adaptation. arXiv preprint, April. find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/qian-2026-why-do-large-language-models/