Elamur Research⌕
☰
home / papers / 2026 / CEMT:Controllable Element-Oriented Machine Translation via Structured Linguistic Reasoning

CEMT:Controllable Element-Oriented Machine Translation via Structured Linguistic Reasoning

Paper · 2026 · Lingling Shi, Haoyu Jin, Ruiyu Fang et al.

Summary

LLM-based translators often mishandle small but critical pieces of input: URLs, handles, HTML tags and emojis that must be copied exactly, and idioms, slang or culture-bound terms that need careful adaptation. Errors include paraphrasing, dropping, or hallucinating these items. CEMT addresses this by mimicking how human translators work: analyse first, plan a strategy, then write.

A frozen Element Detection Module (EDM) first tags the source with three signals: sentence complexity, Do-Not-Translate items, and pragmatic items. A Translation Module, built on Qwen2.5-7B, then produces a structured chain of thought in four stages: semantics & pragmatics, argument structure, syntax, and strategy. Each stage has a general track and an element-focused track. Training combines SFT with GRPO-based RL. A CoT Judge scores the intermediate reasoning steps, not only the final output.

On WMT23/24 Chinese↔English, CEMT outperforms strong 7B open-source baselines while making fewer element-level errors. The work suggests that explicit linguistic structure and process-level rewards can make LLM translation more reliable and interpretable.

Key points

  • EDM setup: The EDM is Qwen2.5-7B fine-tuned on about 4,000 augmented annotated samples. It stays frozen during Translation Module training. Sentence complexity is one of three classes (Complete Simple, Complete Complex, Incomplete) and controls how deep the analysis goes.
  • RL reward: The reward combines three parts:
    • a format term;
    • a translation-quality term (BLEU, XCOMET, COMETKiwi);
    • a process reward from the CoT Judge (Qwen3-235B-A22B), which also drives rejection sampling.
  • Main result: CEMT reports the best average results among 7B open-source systems on WMT23/24 ZH↔EN, including Hunyuan-MT-7B.
  • Zero-shot transfer: Applying element detection alone to Qwen2.5-7B-Instruct improved XCOMET-XL and COMETKiwi-23-XL on all 10 tested language pairs, including cs→uk and en→uk. BLEU dropped slightly in some cases, such as EN→HI and EN→RU.
  • Limitations and code: The full pipeline was tested only on ZH↔EN and only at the 7B scale. The large judge adds training cost, and structured reasoning increases token usage at inference. Code is available at github.com/ther7777/CEMT.

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

🎓Xiamen UniversityXiamen · China21 works · 2,258 citations🏢China TelecomBeijing · China7 works · 16 citations🏢China Telecom (China)Changsha · China6 works · 15 citations

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 works

🧭 Topics 2Research subjects and languages the work is about.Machine translation · 1,087 worksReasoning · 1,426 works

Cite

Cite as Lingling Shi, Haoyu Jin, Ruiyu Fang, Shuangyong Song, Jinsong Su, Yongxiang Li and Xuelong Li. 2026. CEMT:Controllable Element-Oriented Machine Translation via Structured Linguistic Reasoning. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.findings-acl.1882

@inproceedings{shi2026cemt,
  title = {{CEMT:Controllable Element-Oriented Machine Translation via Structured Linguistic Reasoning}},
  author = {Lingling Shi, Haoyu Jin, Ruiyu Fang, Shuangyong Song, Jinsong Su, Yongxiang Li and Xuelong Li},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.1882},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.1882}
}

References

58 references, 27 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 M. Guerreiro, Pedro H. Martins, João Alves, 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-related tasks.…
  2. Hongjun An, Wenhan Hu, Sida Huang, Siqi Huang, Ru-anjun Li, Yuanzhi Liang, Jiawei Shao, Yiliang Song, Zihan Wang, Cheng Yuan, Chi Zhang, Hongyuan Zhang, Wenhao Zhuang, and Xuelong Li. 2025. Ai flow: Perspectives, scenarios, and approaches. Preprint, arXiv:2506.12479. — [arXiv:2506.12479](https://arxiv.org/abs/2506.12479) find
  3. Anthropic. 2024. Claude 3.5 sonnet model card addendum. find
  4. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, and… find
  5. Wenhan Chang, Tianqing Zhu, Yu Zhao, Shuangyong Song, Ping Xiong, and Wanlei Zhou. 2026. Chain-of-lure: A universal jailbreak attack framework using unconstrained synthetic narratives. Preprint, arXiv:2505.17519. — [arXiv:2505.17519](https://arxiv.org/abs/2505.17519) find
  6. Huadong Chen, Shujian Huang, David Chiang, and Jiajun Chen. 2017. Improved neural machine translation with a syntax-aware encoder and decoder. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1936–1945, Vancouver, Canada. Assoc…
  7. Jinyang Chen, Haolun Wu, Jianhong Pang, Yihua Wang, Dell Zhang, and Changzhi Sun. 2025. Tool learning with language models: a comprehensive survey of methods, pipelines, and benchmarks. Vicinagearth, 2(1):16. find
  8. David Dale, Elena Voita, Loic Barrault, and Marta R. Costa-jussà. 2023. Detecting and mitigating hallucinations in machine translation: Model internal workings alone do well, sentence similarity Even better. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (…
  9. DeepSeek-AI, Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, Xiaokang Zhang, Xingkai Yu, Yu Wu, Z. F. Wu, Zhibin Gou, Zhihong Shao, Zhuoshu Li, Ziyi Gao, and 181 others. 2025. Deepseek-r1: Incentivizing reasoning capability in ll…
  10. Akiko Eriguchi, Kazuma Hashimoto, and Yoshimasa Tsuruoka. 2016. Tree-to-sequence attentional neural machine translation. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 823–833, Berlin, Germany. Association for Computational L… find
  11. Zhaopeng Feng, Shaosheng Cao, Jiahan Ren, Jiayuan Su, Ruizhe Chen, Yan Zhang, Jian Wu, and Zuozhu Liu. 2025a. MT-r1-zero: Advancing LLM-based machine translation via r1-zero-like reinforcement learning. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 18685– 18702, Suz… find
  12. Zhaopeng Feng, Yan Zhang, Hao Li, Bei Wu, Jiayu Liao, Wenqiang Liu, Jun Lang, Yang Feng, Jian Wu, and Zuozhu Liu. 2025b. TEaR: Improving LLM-based machine translation with systematic self-refinement. In Findings of the Association for Computational Linguistics: NAACL 2025, pages 3922–3938, Albuquerq… find
  13. Yuan Gao, Ruili Wang, and Feng Hou. 2024. 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, New York, NY, USA. Association for Computing Machinery. find
  14. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Alex Vaughan, Amy Yang, Angela Fan, Anirudh Goyal, Anthony Hartshorn, Aobo Yang, Archi Mitra, Archie Sravankumar, Artem Korenev, Arthur Hinsvark, and 542 o… — The Llama 3 Herd of Models
  15. Nuno M. Guerreiro, Duarte M. Alves, Jonas Waldendorf, Barry Haddow, Alexandra Birch, Pierre Colombo, and André F. T. Martins. 2023. Hallucinations in large multilingual translation models. Transactions of the Association for Computational Linguistics, 11:1500–1517.
  16. Nuno M. Guerreiro, Ricardo Rei, Daan van Stigt, Luisa Coheur, Pierre Colombo, and André F. T. Martins. 2024. xCOMET: Transparent machine translation evaluation through fine-grained error detection. Transactions of the Association for Computational Linguistics, 12:979–995.
  17. Minggui He, Yilun Liu, Shimin Tao, Yuanchang Luo, Hongyong Zeng, Chang Su, Li Zhang, Hongxia Ma, Daimeng Wei, Weibin Meng, Hao Yang, Boxing Chen, and Osamu Yoshie. 2025. R1-t1: Fully incentivizing translation capability in llms via reasoning learning. Preprint, arXiv:2502.19735.
  18. Zhongjiang He, Zihan Wang, Xinzhang Liu, Shixuan Liu, Yitong Yao, Yuyao Huang, Xuelong Li, Yongxiang Li, Zhonghao Che, Zhaoxi Zhang, Yan Wang, Xin Wang, Luwen Pu, Huinan Xu, Ruiyu Fang, Yu Zhao, Jie Zhang, Xiaomeng Huang, Zhilong Lu, and 17 others. 2024. Telechat technical report. Preprint, arXiv:24…
  19. 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. ArXiv, abs/2302.09210. find
  20. J. Edward Hu, Huda Khayrallah, Ryan Culkin, Patrick Xia, Tongfei Chen, Matt Post, and Benjamin Van Durme. 2019. Improved lexically constrained decoding for translation and monolingual rewriting. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational…
  21. Xuancheng Huang, Zijun Liu, Peng Li, Tao Li, Maosong Sun, and Yang Liu. 2023. An extensible plug-and-play method for multi-aspect controllable text generation. Preprint, arXiv:2212.09387. find
  22. Zhongjiang He, Zhongyuan Wang, Xuelong Li, and Tiejun Huang. 2024a. 52b to 1t: Lessons learned via tele-flm series. Preprint, arXiv:2407.02783. — [arXiv:2407.02783](https://arxiv.org/abs/2407.02783) find
  23. Xiang Li, Yiqun Yao, Xin Jiang, Xuezhi Fang, Chao Wang, Xinzhang Liu, Zihan Wang, Yu Zhao, Xin Wang, Yuyao Huang, Shuangyong Song, Yongxiang Li, Zheng Zhang, Bo Zhao, Aixin Sun, Yequan Wang, Zhongjiang He, Zhongyuan Wang, Xuelong Li, and Tiejun Huang. 2024b. Tele-flm technical report. Preprint, arXi… — [arXiv:2404.16645](https://arxiv.org/abs/2404.16645) find
  24. Zheng Li, Mao Zheng, Mingyang Song, and Wenjie Yang. 2025a. Tat-r1: Terminology-aware translation with reinforcement learning and word alignment. Preprint, arXiv:2505.21172. — [arXiv:2505.21172](https://arxiv.org/abs/2505.21172) find
  25. Zhongqiu Li, Shiquan Wang, Ruiyu Fang, Mengjiao Bao, Zhenhe Wu, Shuangyong Song, Yongxiang Li, and Zhongjiang He. 2025b. MR-UIE: multi-perspective reasoning with reinforcement learning for universal information extraction. Vicinagearth, 2(1):17. find
  26. Aaron Hurst, Adam Lerer, Adam P. Goucher, Adam Perelman, Aditya Ramesh, Aidan Clark, AJ Ostrow, Akila Welihinda, Alan Hayes, Alec Radford, Aleksander Madry, Alex Baker-Whitcomb, Alex Beutel, Alex Borzunov, Alex Carney, Alex Chow, Alex Kirillov, Alex Nichol, Alex Paino, and 79 others. 2024. Gpt-4o sy…
  27. Hunter Lightman, Vineet Kosaraju, Yuri Burda, Harrison Edwards, Bowen Baker, Teddy Lee, Jan Leike, John Schulman, Ilya Sutskever, and Karl Cobbe. 2024. Let’s verify step by step. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. Open-Rev…
  28. Wenxiang Jiao, Wenxuan Wang, Jen tse Huang, Xing Wang, Shuming Shi, and Zhaopeng Tu. 2023. Is chatgpt a good translator? yes with gpt-4 as the engine.
  29. Xinzhang Liu, Chao Wang, Zhihao Yang, Zhuo Jiang, Xuncheng Zhao, Haoran Wang, Lei Li, Dongdong He, Luobin Liu, Kaizhe Yuan, Han Gao, Zihan Wang, Yitong Yao, Sishi Xiong, Wenmin Deng, Haowei He, Kaidong Yu, Yu Zhao, Ruiyu Fang, and 35 others. 2025. Training report of telechat3-moe. Preprint, arXiv:25… — [arXiv:2512.24157](https://arxiv.org/abs/2512.24157) find
  30. Tom Kocmi, 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 Popov… — Findings of the WMT24 General Machine Translation Shared Task: The LLM Era Is Here but MT Is Not Solved Yet
  31. Tom Kocmi, Eleftherios Avramidis, Rachel Bawden, Ondřej Bojar, Anton Dvorkovich, Christian Federmann, Mark Fishel, Markus Freitag, Thamme Gowda, Roman Grundkiewicz, Barry Haddow, Philipp Koehn, Benjamin Marie, Christof Monz, Makoto Morishita, Kenton Murray, Masaaki Nagata, Toshiaki Nakazawa, Martin… find
  32. Xiang Li, Yiqun Yao, Xin Jiang, Xuezhi Fang, Chao Wang, Xinzhang Liu, Zihan Wang, Yu Zhao, Xin Wang, Yuyao Huang, Shuangyong Song, Yongxiang Li, Zheng Zhang, Bo Zhao, Aixin Sun, Yequan Wang, Diego Marcheggiani, Jasmijn Bastings, and Ivan Titov. 2018. Exploiting semantics in neural machine translatio… find
  33. Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul F Christiano, Jan Leike, and Ryan Lowe. 2022. Tra… — Training language models to follow instructions with human feedback
  34. Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pages 311–318, Philadelphia, Pennsylvania, USA. Association for Computational…
  35. Matt Post and David Vilar. 2018. Fast lexically constrained decoding with dynamic beam allocation for neural machine translation. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers),…
  36. Ricardo Rei, Nuno M. Guerreiro, José Pombal, Daan van Stigt, Marcos Treviso, Luisa Coheur, José G. C. de Souza, and André F. T. Martins. 2023. Scaling up CometKiwi: Unbabel-IST 2023 submission for the quality estimation shared task. In Proceedings of the Eighth Conference on Machine Translation, pag…
  37. Rico Sennrich and Barry Haddow. 2016. Linguistic input features improve neural machine translation. In Proceedings of the First Conference on Machine Translation: Volume 1, Research Papers, pages 83– 91, Berlin, Germany. Association for Computational Linguistics.
  38. Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Xiao Bi, Haowei Zhang, Mingchuan Zhang, Y. K. Li, Y. Wu, and Daya Guo. 2024. Deepseekmath: Pushing the limits of mathematical reasoning in open language models. Preprint, arXiv:2402.03300.
  39. Huacheng Song and Hongzhi Xu. 2024. A deep analysis of the impact of multiword expressions and named entities on Chinese-English machine translations. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 6154–6165, Miami, Florida, USA. Association for Computational Linguis… find
  40. Richard S. Sutton and Andrew G. Barto. 2018. Reinforcement Learning: An Introduction, 2 edition. MIT Press, Cambridge, MA. find
  41. Gemini Team, Petko Georgiev, Ving Ian Lei, Ryan Burnell, Libin Bai, Anmol Gulati, Garrett Tanzer, Damien Vincent, Zhufeng Pan, Shibo Wang, Soroosh Mariooryad, Yifan Ding, Xinyang Geng, Fred Alcober, Roy Frostig, Mark Omernick, Lexi Walker, Cosmin Paduraru, Christina Sorokin, and 1118 others. 2024. G… — Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
  42. 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, and 20 o… find
  43. Jonathan Uesato, Nate Kushman, Ramana Kumar, Francis Song, Noah Siegel, Lisa Wang, Antonia Creswell, Geoffrey Irving, and Irina Higgins. 2022. Solving math word problems with process-and outcome-based feedback. arXiv preprint arXiv:2211.14275.
  44. 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, pages 6770–6782, Vienna, Austria. Association for Computational Linguistics. find
  45. Jiaan Wang, Fandong Meng, and Jie Zhou. 2025b. Deeptrans: Deep reasoning translation via reinforcement learning. Preprint, arXiv:2504.10187.
  46. Jiaan Wang, Fandong Meng, and Jie Zhou. 2025c. Extrans: Multilingual deep reasoning translation via exemplar-enhanced reinforcement learning. Preprint, arXiv:2505.12996. — [arXiv:2505.12996](https://arxiv.org/abs/2505.12996) find
  47. Zihan Wang, XinZhang Liu, Shixuan Liu, Yitong Yao, Yunyao Huang, Mengxiang Li, Zhongjiang He, Yongxian Li, Luwen Pu, Huinan Xu, Chao Wang, and Shuangyong Song. 2024. TeleChat: An open-source billingual large language model. In Proceedings of the 10th SIGHAN Workshop on Chinese Language Processing (S… find
  48. Zihan Wang, Xinzhang Liu, Yitong Yao, Chao Wang, Yu Zhao, Zhihao Yang, Wenmin Deng, Kaipeng Jia, Jiaxin Peng, Yuyao Huang, Sishi Xiong, Zhuo Jiang, Kaidong Yu, Xiaohui Hu, Fubei Yao, Ruiyu Fang, Zhuoru Jiang, Ruiting Song, Qiyi Xie, and 19 others. 2025d. Technical report of telechat2, telechat2.5 an… — [arXiv:2507.18013](https://arxiv.org/abs/2507.18013) find
  49. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed H. Chi, Quoc V. Le, and Denny Zhou. 2022. Chain-of-thought prompting elicits reasoning in large language models. In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processi…
  50. Di Wu, Ruiyu Fang, Liting Jiang, Shuangyong Song, Xiaomeng Huang, Shiquan Wang, Zhongqiu Li, Lingling Shi, Mengjiao Bao, Yongxiang Li, and Hao Huang. 2025a. Multi-intent spoken language understanding: a survey of methods, trends, and challenges. Vicinagearth, 2(1):20. find
  51. Zhenhe Wu, Jian Yang, Jiaheng Liu, Xianjie Wu, Changzai Pan, Jie Zhang, Yu Zhao, Shuangyong Song, Yongxiang Li, and Zhoujun Li. 2025b. Tabler1: Region-based reinforcement learning for table understanding. Preprint, arXiv:2505.12415. — [arXiv:2505.12415](https://arxiv.org/abs/2505.12415) find
  52. Haoran Xu, Kenton Murray, Philipp Koehn, Hieu Hoang, Akiko Eriguchi, and Huda Khayrallah. 2025. find
  53. X-ALMA: plug & play modules and adaptive rejection for quality translation at scale. In The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025. OpenReview.net. find
  54. An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, Huan Lin, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Yang, Jiaxi Yang, Jingren Zhou, Junyang Lin, Kai Dang, and 22 others. 2024. Qwen2.5 technical report. CoRR, abs/2412.1511… find
  55. Wenjie Yang, Mao Zheng, Mingyang Song, Zheng Li, and Sitong Wang. 2025. Ssr-zero: Simple self-rewarding reinforcement learning for machine translation. Preprint, arXiv:2505.16637.
  56. Yang Yue, Zhiqi Chen, Rui Lu, Andrew Zhao, Zhaokai Wang, Yang Yue, Shiji Song, and Gao Huang. 2025. Does reinforcement learning really incentivize reasoning capacity in llms beyond the base model? Preprint, arXiv:2504.13837.
  57. Wei Zhang, Xiangyuan Guan, Lu Yunhong, Jie Zhang, Shuangyong Song, Xianfu Cheng, Zhenhe Wu, and Zhoujun Li. 2025. Lemur: Log parsing with entropy sampling and chain-of-thought merging. Preprint, arXiv:2402.18205. — [arXiv:2402.18205](https://arxiv.org/abs/2402.18205) find
  58. Mao Zheng, Zheng Li, Bingxin Qu, Mingyang Song, Yang Du, Mingrui Sun, and Di Wang. 2025. Hunyuan-mt technical report. Preprint, arXiv:2509.05209.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/shi-2026-cemt-controllable-element-oriented-machine/