Elamur Research⌕
☰
home / papers / 2026 / M²PO: Multi-Perspective Multi-Pair Preference Optimization for Machine Translation

M²PO: Multi-Perspective Multi-Pair Preference Optimization for Machine Translation

Paper · 2026 · Hao Wang, Linlong Xu, Heng Liu et al.

Summary

The paper tackles unreliable reward signals in preference-based alignment of LLMs for machine translation. Using the HalOmi benchmark, the authors show that neural QE metrics (XCOMET, KIWI-XXL) handle clearly good and clearly bad outputs well. They become unreliable in a mid-range coverage band (30–80), which they call the "Zone of Uncertainty". Partial hallucinations and omissions cluster there, and fluent but unfaithful outputs often get inflated scores. The base model's average log probability, by contrast, tracks faithfulness monotonically.

Their framework, M$^2$PO, has two parts. First, it builds preferences from several signals: a QE score, a discrete faithfulness coefficient (SAC), and model confidence, blended through a dynamic curriculum. Second, it trains on multiple chosen/rejected pairs from the full candidate list with a CPO-style loss, plus a global ranking loss. They apply it to Qwen3-4B-Instruct and GemmaX2-28-9B across six directions on WMT23, WMT24 and FLORES-200. The 9B model beats its data generator GPT-4o-mini and larger open models, and roughly matches GPT-4o and Gemini-2.0-Flash. The main implication is that careful preference construction can let compact open models produce faithful translations.

Key points

  • Faithfulness is measured with Coverage Score, an LLM-based metric implemented with Gemini-2.0-Flash following the WAP approach. Candidates come from GPT-4o-mini, and the code is published in the AIDC-AI/Marco-MT GitHub repo (MMPO folder).
  • On WMT23, GemmaX2-28-9B-M$^2$PO reaches 97.87 Coverage and 89.67 XCOMET, up from the base model's 96.09 and 87.16.
  • In the ablations, dropping the dynamic multi-pair CPO loss hurts most (−1.11 Coverage, −1.58 XCOMET). Removing SAC, the dynamic fusion curriculum, the multi-pair contrast, or the ranking loss also lowers scores.
  • A fully open-source pipeline still beats plain CPO by +0.63 Coverage and +0.74 XCOMET. This pipeline generates candidates with the base model and labels SAC with Gemma-3-27B-it.
  • The gains hold when MetricX-24-XXL replaces KIWI-XXL as the reward proxy. The stated limitations are that 70B+ models and low-resource languages were not tested, and that the main pipeline depends on proprietary APIs.

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

🏢Alibaba GroupHangzhou · China168 works · 15,386 citations🎓Hunan UniversityChangsha · China3 works · 304 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 1Research subjects and languages the work is about.Machine translation · 1,087 works

Cite

Cite as Hao Wang, Linlong Xu, Heng Liu, Yangyang Liu, Xiaohu Zhao, Bo Zeng, Liangying Shao, Yichen Dong, Xinwei Wu, Jiang Zhou, Tianyu Dong, Xiangxiang Zeng, Longyue Wang and Weihua Luo. 2026. M²PO: Multi-Perspective Multi-Pair Preference Optimization for Machine Translation. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.acl-long.469

@inproceedings{wang2026multi,
  title = {{M²PO: Multi-Perspective Multi-Pair Preference Optimization for Machine Translation}},
  author = {Hao Wang, Linlong Xu, Heng Liu, Yangyang Liu, Xiaohu Zhao, Bo Zeng, Liangying Shao, Yichen Dong, Xinwei Wu, Jiang Zhou, Tianyu Dong, Xiangxiang Zeng, Longyue Wang and Weihua Luo},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.469},
  url = {https://doi.org/10.18653/v1/2026.acl-long.469}
}

References

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

  1. Aakanksha, Arash Ahmadian, Beyza Ermis, Seraphina Goldfarb-Tarrant, Julia Kreutzer, Marzieh Fadaee, and Sara Hooker. 2024. The multilingual alignment prism: Aligning global and local preferences to reduce harm. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing…
  2. Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, and 1 others. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774.
  3. Sweta Agrawal, José G. C. De Souza, Ricardo Rei, António Farinhas, Gonçalo Faria, Patrick Fernandes, Nuno M Guerreiro, and Andre Martins. 2024. Modeling user preferences with automatic metrics: Creating a high-quality preference dataset for machine translation. In Proceedings of the 2024 Conference… find
  4. Duarte M. Alves, José Pombal, Nuno Miguel Guerreiro, Pedro Henrique Martins, João Alves, M. Amin Farajian, Ben Peters, Ricardo Rei, Patrick Fernandes, Sweta Agrawal, Pierre Colombo, José G. C. de Souza, and André F. T. Martins. 2024. Tower: An open multilingual large language model for translation-r…
  5. Viraat Aryabumi, John Dang, Dwarak Talupuru, Saurabh Dash, David Cairuz, Hangyu Lin, Bharat Venkitesh, Madeline Smith, Jon Ander Campos, Yi Chern Tan, Kelly Marchisio, Max Bartolo, Sebastian Ruder, Acyr Locatelli, Julia Kreutzer, Nick Frosst, Aidan N. Gomez, Phil Blunsom, Marzieh Fadaee, and 2 other… — Aya 23: Open Weight Releases to Further Multilingual Progress
  6. Zhe Cao, Tao Qin, Tie-Yan Liu, Ming-Feng Tsai, and Hang Li. 2007. Learning to rank: from pairwise approach to listwise approach. In ICML, volume 227 of ACM International Conference Proceeding Series, pages 129–136. ACM. find
  7. Mauro Cettolo, Marcello Federico, Luisa Bentivogli, Jan Niehues, Sebastian Stüker, Katsuhito Sudoh, Koichiro Yoshino, and Christian Federmann. 2017. Overview of the IWSLT 2017 evaluation campaign. In Proceedings of the 14th International Conference on Spoken Language Translation, Tokyo, Japan. Inter…
  8. Andong Chen, Lianzhang Lou, Kehai Chen, Xuefeng Bai, Yang Xiang, Muyun Yang, Tiejun Zhao, and Min Zhang. 2025. Benchmarking LLMs for translating classical Chinese poetry: Evaluating adequacy, fluency, and elegance. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Proces…
  9. Gheorghe Comanici, Eric Bieber, Mike Schaekermann, Ice Pasupat, Noveen Sachdeva, Inderjit Dhillon, Marcel Blistein, Ori Ram, Dan Zhang, Evan Rosen, and 1 others. 2025. Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities. arX…
  10. Marta R Costa-Jussà, James Cross, Onur Çelebi, Maha Elbayad, Kenneth Heafield, Kevin Heffernan, Elahe Kalbassi, Janice Lam, Daniel Licht, Jean Maillard, and 1 others. 2022. No language left behind: Scaling human-centered machine translation. arXiv preprint arXiv:2207.04672. find
  11. Menglong Cui, Pengzhi Gao, Wei Liu, Jian Luan, and Bin Wang. 2025. Multilingual machine translation with open large language models at practical scale: An empirical study. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: H… find
  12. David Dale, Elena Voita, Loic Barrault, and Marta R. Costa-jussà. 2023a. 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…
  13. David Dale, Elena Voita, Janice Lam, Prangthip Hansanti, Christophe Ropers, Elahe Kalbassi, Cynthia Gao, Loïc Barrault, and Marta R. Costa-jussà. 2023b. HalOmi: A manually annotated benchmark for multilingual hallucination and omission detection in machine translation. In Proceedings of the 2023 Con… find
  14. John Dang, Shivalika Singh, Daniel D’souza, Arash Ahmadian, Alejandro Salamanca, Madeline Smith, Aidan Peppin, Sungjin Hong, Manoj Govindassamy, Terrence Zhao, and 1 others. 2024. Aya expanse: Combining research breakthroughs for a new multilingual frontier. arXiv preprint arXiv:2412.04261.
  15. DeepSeek-AI. 2025. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. CoRR, abs/2501.12948.
  16. Daniel Deutsch, Rotem Dror, and Dan Roth. 2022. On the limitations of reference-free evaluations of generated text. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics. find
  17. Yichen Dong, Xinglin Lyu, Junhui Li, Daimeng Wei, Min Zhang, Shimin Tao, and Hao Yang. 2025. Two intermediate translations are better than one: Fine-tuning LLMs for document-level translation refinement. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volu… find
  18. Kawin Ethayarajh, Winnie Xu, Niklas Muennighoff, Dan Jurafsky, and Douwe Kiela. 2024. KTO: model alignment as prospect theoretic optimization. CoRR, abs/2402.01306. find
  19. 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, Suzhou, China. Associat… find
  20. Zhaopeng Feng, Jiahan Ren, Jiayuan Su, Jiamei Zheng, Hongwei Wang, and Zuozhu Liu. 2025b. MT-RewardTree: A comprehensive framework for advancing LLM-based machine translation via reward modeling. In Findings of the Association for Computational Linguistics: EMNLP 2025, Suzhou, China. Association for… find
  21. Evangelia Gogoulou, Shorouq Zahra, Liane Guillou, Luise Dürlich, and Joakim Nivre. 2025. Can LLMs detect intrinsic hallucinations in paraphrasing and machine translation? In Proceedings of the Fourth Workshop on Generation, Evaluation and Metrics (GEM 2 ), Vienna, Austria and virtual meeting. Associ… find
  22. 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.
  23. 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.
  24. Taneesh Gupta, Rahul Madhavan, Xuchao Zhang, Nagarajan Natarajan, Chetan Bansal, and Saravan Rajmohan. 2025. Multi-preference optimization: Generalizing dpo via set-level contrasts. Preprint, arXiv:2412.04628. — [arXiv:2412.04628](https://arxiv.org/abs/2412.04628) find
  25. 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. CoRR, abs/2502.19735.
  26. Zhiwei He, Xing Wang, Wenxiang Jiao, Zhuosheng Zhang, Rui Wang, Shuming Shi, and Zhaopeng Tu. 2024. Improving machine translation with human feedback: An exploration of quality estimation as a reward model. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Co… find
  27. Anas Himmi, Guillaume Staerman, Marine Picot, Pierre Colombo, and Nuno M Guerreiro. 2024. Enhanced hallucination detection in neural machine translation through simple detector aggregation. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, Miami, Florida, USA… find
  28. Jiwoo Hong, Noah Lee, and James Thorne. 2024. ORPO: Monolithic preference optimization without reference model. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, Miami, Florida, USA. Association for Computational Linguistics. find
  29. 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. In ICLR. OpenReview.net.
  30. Aaron Hurst, Adam Lerer, Adam P Goucher, Adam Perelman, Aditya Ramesh, Aidan Clark, AJ Ostrow, Akila Welihinda, Alan Hayes, Alec Radford, and 1 others. 2024. Gpt-4o system card. arXiv preprint arXiv:2410.21276.
  31. Albert Q Jiang, Alexandre Sablayrolles, Antoine Roux, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Emma Bou Hanna, Florian Bressand, and 1 others. 2024. Mixtral of experts. arXiv preprint arXiv:2401.04088. find
  32. Ruili Jiang, Kehai Chen, Xuefeng Bai, Zhixuan He, Juntao Li, Muyun Yang, Tiejun Zhao, Liqiang Nie, and Min Zhang. 2025. A survey on human preference learning for aligning large language models. ACM Computing Surveys, 58(6):1–39. find
  33. 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
  34. 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
  35. Tom Kocmi, Rachel Bawden, Ondřej Bojar, Anton Dvorkovich, Christian Federmann, Mark Fishel, Thamme Gowda, Yvette Graham, Roman Grundkiewicz, Barry Haddow, Rebecca Knowles, Philipp Koehn, Christof Monz, Makoto Morishita, Masaaki Nagata, Toshiaki Nakazawa, Michal Novák, Martin Popel, and Maja Popovic… find
  36. Woosuk Kwon, 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 SOSP, pages 611–626. ACM.
  37. Tianjiao Li, Mengran Yu, Chenyu Shi, Yanjun Zhao, Xiaojing Liu, Qi Zhang, Xuanjing Huang, Qiang Zhang, and Jiayin Wang. 2025. RIVAL: Reinforcement learning with iterative and adversarial optimization for machine translation. In Findings of the Association for Computational Linguistics: EMNLP 2025, S… find
  38. Tianqi Liu, Zhen Qin, Junru Wu, Jiaming Shen, Misha Khalman, Rishabh Joshi, Yao Zhao, Mohammad Saleh, Simon Baumgartner, Jialu Liu, Peter J Liu, and Xuanhui Wang. 2025. LiPO: Listwise preference optimization through learning-to-rank. In Proceedings of the 2025 Conference of the Nations of the Americ…
  39. Ilya Loshchilov and Frank Hutter. 2019. Decoupled weight decay regularization. In ICLR (Poster). Open-Review.net. find
  40. Yinquan Lu, Wenhao Zhu, Lei Li, Yu Qiao, and Fei Yuan. 2024. LLaMAX: Scaling linguistic horizons of LLM by enhancing translation capabilities beyond 100 languages. In Findings of the Association for Computational Linguistics: EMNLP 2024, Miami, Florida, USA. Association for Computational Linguistics… find
  41. Xinglin Lyu, Wei Tang, Yuang Li, Xiaofeng Zhao, Ming Zhu, Junhui Li, Yunfei Lu, Min Zhang, Daimeng Wei, Hao Yang, and Min Zhang. 2025. DoCIA: An online document-level context incorporation agent for speech translation. In Findings of the Association for Computational Linguistics: ACL 2025, Vienna, A… find
  42. Yu Meng, Mengzhou Xia, and Danqi Chen. 2024. Simpo: Simple preference optimization with a reference-free reward. Advances in Neural Information Processing Systems, 37:124198–124235. find
  43. Jacob Menick, Kevin Lu, Shengjia Zhao, E Wallace, H Ren, H Hu, N Stathas, and F Petroski Such. 2024. Gpt-4o mini: advancing cost-efficient intelligence. Open AI: San Francisco, CA, USA. find
  44. Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll L. 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.… — Training language models to follow instructions with human feedback
  45. Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D. Manning, Stefano Ermon, and Chelsea Finn. 2023. Direct preference optimization: Your language model is secretly a reward model. In NeurIPS.
  46. Miguel Moura Ramos, Tomás Almeida, Daniel Vareta, Filipe Azevedo, Sweta Agrawal, Patrick Fernandes, and André F. T. Martins. 2024. Fine-grained reward optimization for machine translation using error severity mappings. CoRR, abs/2411.05986.
  47. 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, Sin…
  48. Ricardo Rei, Nuno Miguel Guerreiro, José Pombal, João Alves, Pedro Teixeirinha, M. Amin Farajian, and André F. T. Martins. 2025. Tower+: Bridging generality and translation specialization in multilingual llms. CoRR, abs/2506.17080. find
  49. Ricardo Rei, Craig Stewart, Ana C Farinha, and Alon Lavie. 2020. COMET: A neural framework for MT evaluation. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Online. Association for Computational Linguistics.
  50. John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. CoRR, abs/1707.06347. find
  51. Shuaijie She, Wei Zou, Shujian Huang, Wenhao Zhu, Xiang Liu, Xiang Geng, and Jiajun Chen. 2024. MAPO: Advancing multilingual reasoning through multilingual-alignment-as-preference optimization. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long…
  52. Haoxiang Sun, Ruize Gao, Pei Zhang, Baosong Yang, and Rui Wang. 2025. Enhancing machine translation with self-supervised preference data. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Vienna, Austria. Association for Computational… find
  53. Shaomu Tan and Christof Monz. 2025. ReMedy: Learning machine translation evaluation from human preferences with reward modeling. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, Suzhou, China. Association for Computational Linguistics. find
  54. Jannis Vamvas and Rico Sennrich. 2022. As little as possible, as much as necessary: Detecting over- and undertranslations with contrastive conditioning. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), Dublin, Ireland. Association f… find
  55. Di Wu, Yibin Lei, and Christof Monz. 2025. Calibrating translation decoding with quality estimation on llms. CoRR, abs/2504.19044. find
  56. Qiyu Wu, Masaaki Nagata, Zhongtao Miao, and Yoshimasa Tsuruoka. 2024. Word alignment as preference for machine translation. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, Miami, Florida, USA. Association for Computational Linguistics. find
  57. Qiyu Wu, Masaaki Nagata, and Yoshimasa Tsuruoka. 2023. WSPAlign: Word alignment pre-training via large-scale weakly supervised span prediction. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Toronto, Canada. Association for Computa… find
  58. Haoran Xu, Young Jin Kim, Amr Sharaf, and Hany Hassan Awadalla. 2024a. A paradigm shift in machine translation: Boosting translation performance of large language models. In ICLR. OpenReview.net. find
  59. Haoran Xu, Kenton Murray, Philipp Koehn, Hieu Hoang, Akiko Eriguchi, and Huda Khayrallah. 2025. X-ALMA: plug & play modules and adaptive rejection for quality translation at scale. In ICLR. Open-Review.net. find
  60. Haoran Xu, Amr Sharaf, Yunmo Chen, Weiting Tan, Lingfeng Shen, Benjamin Van Durme, Kenton Murray, and Young Jin Kim. 2024b. Contrastive preference optimization: Pushing the boundaries of LLM performance in machine translation. In ICML. Open-Review.net.
  61. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, and 1 others. 2025a. Qwen3 technical report. arXiv preprint arXiv:2505.09388.
  62. Wen Yang, Junhong Wu, Chen Wang, Chengqing Zong, and Jiajun Zhang. 2025b. Implicit cross-lingual rewarding for efficient multilingual preference alignment. In Findings of the Association for Computational Linguistics: ACL 2025, Vienna, Austria. Association for Computational Linguistics. find
  63. Wen Yang, Junhong Wu, Chen Wang, Chengqing Zong, and Jiajun Zhang. 2025c. Language imbalance driven rewarding for multilingual self-improving. In ICLR. OpenReview.net. find
  64. Zonghan Yang, Yong Cheng, Yang Liu, and Maosong Sun. 2019. Reducing word omission errors in neural machine translation: A contrastive learning approach. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy. Association for Computational Linguist… find
  65. Jiali Zeng, Fandong Meng, Yongjing Yin, and Jie Zhou. 2024. Teaching large language models to translate with comparison. In AAAI, pages 19488–19496. AAAI Press. find
  66. Hongbin Zhang, Kehai Chen, Xuefeng Bai, Yang Xiang, and Min Zhang. 2024. Paying more attention to source context: Mitigating unfaithful translations from large language model. In Findings of the Association for Computational Linguistics: ACL 2024, Bangkok, Thailand. Association for Computational Lin… find
  67. Chujie Zheng, Shixuan Liu, Mingze Li, Xiong-Hui Chen, Bowen Yu, Chang Gao, Kai Dang, Yuqiong Liu, Rui Men, An Yang, Jingren Zhou, and Junyang Lin. 2025. Group sequence policy optimization. CoRR, abs/2507.18071.
  68. Training Translation Output Testing KIWI-XXL SAC XCOMET Coverage Source (zh→en): 口水鸡应该是熟的，但收到的是生肉，没办法吃 GemmaX2-28-9B The cold chicken should be cooked, but what I received was raw meat, making it inedible. 62.01 High Partial 85.57 GPT-4o-mini The mouth-watering chicken should be cooked, but what I r… find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/wang-2026-m-2-po-multi-perspective/