Elamur Research⌕
☰
home / papers / 2026 / Incentivizing Parametric Knowledge via Reinforcement Learning with Verifiable Rewards for Cross-Cultural Entity Translation

Incentivizing Parametric Knowledge via Reinforcement Learning with Verifiable Rewards for Cross-Cultural Entity Translation

Paper · 2026 · Jiang Zhou, Xiaohu Zhao, Xinwei Wu et al.

Summary

Large language models often mistranslate culturally grounded entities such as songs, films, books, places and idioms. They copy the source term or render it literally or phonetically, even though sampling many outputs (pass@128) shows the right name is often already in the model's knowledge. The authors propose EA-RLVR, a reinforcement learning framework that draws out this stored knowledge without external retrieval or knowledge bases. The model writes a reasoning trace and then a translation. A rule-based verifier scores the output: format and length gates must pass first, and a bonus is added when the translation contains a gold entity name. Optimization is critic-free. On XC-Translate, training on about 7k examples raises entity accuracy on a 50k test set of entirely unseen entities. The gains carry over to general translation quality on WMT24pp and transfer across unrelated language groups. This matters because it shows deterministic, verifiable rewards can make entity-aware translation work without retrieval infrastructure. The authors also found that neural quality metrics fail to supervise correct entity choice.

Key points

  • Reward design: an output that passes both structural gates (a <think>…</think> format and a length cap relative to the reference) earns 0.2. A normalized substring match against a gold alias set derived from Wikidata adds +1, for a maximum of 1.2. Failing either gate gives 0.
  • Entity accuracy: Qwen3-14B improves from 23.66% to 31.87% on the 50k unseen-entity test set. Across model scales the gains are +8.21 to +9.06 points, and the 14B model reportedly beats a 235B baseline on unseen entities.
  • General translation: XCOMET on WMT24pp rises by +1.25 to +1.35, although XCOMET is never used as a training signal. With the full dataset and 1,000 training steps, the gain grows to +1.59 to +1.68.
  • Cross-lingual transfer (Qwen3-8B): Group A covers ar, ja, ko, th and zh; Group B covers de, es, fr, it and tr. Training on one group and testing on the other improves entity accuracy by +7.27 (A→B) and +6.28 (B→A).
  • Limitations:
    • The method only elicits knowledge the model already has. It cannot handle entities absent from pre-training data, though it combines well with retrieval.
    • A gap remains between pass@1 and pass@128 performance.
    • Strict substring matching may penalize valid variants that are not in the alias list.

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🎓Tianjin UniversityTianjin · China41 works · 1,128 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

Cite

Cite as Jiang Zhou, Xiaohu Zhao, Xinwei Wu, Tianyu Dong, Hao Wang, Yangyang Liu, Heng Liu, Linlong Xu, Longyue Wang, Weihua Luo and Deyi Xiong. 2026. Incentivizing Parametric Knowledge via Reinforcement Learning with Verifiable Rewards for Cross-Cultural Entity 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.254

@inproceedings{zhou2026incentivizing,
  title = {{Incentivizing Parametric Knowledge via Reinforcement Learning with Verifiable Rewards for Cross-Cultural Entity Translation}},
  author = {Jiang Zhou, Xiaohu Zhao, Xinwei Wu, Tianyu Dong, Hao Wang, Yangyang Liu, Heng Liu, Linlong Xu, Longyue Wang, Weihua Luo and Deyi Xiong},
  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.254},
  url = {https://doi.org/10.18653/v1/2026.acl-long.254}
}

References

47 references, 17 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Sweta Agrawal, Chunting Zhou, Mike Lewis, Luke Zettlemoyer, and Marjan Ghazvininejad. 2023. In-context examples selection for machine translation. In Findings of the Association for Computational Linguistics: ACL 2023, pages 8857–8873, Toronto, Canada. Association for Computational Linguistics.
  2. Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde de Oliveira Pinto, Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, Alex Ray, Raul Puri, Gretchen Krueger, Michael Petrov, Heidy Khlaaf, Girish Sastry, Pamela Mishkin, Brooke Chan, Scott Gray, and 39 others. 202… — Evaluating Large Language Models Trained on Code
  3. Simone Conia, Daniel Lee, Min Li, Umar Farooq Minhas, Saloni Potdar, and Yunyao Li. 2024. Towards cross-cultural machine translation with retrieval-augmented generation from multilingual knowledge graphs. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, page… find
  4. Runpeng Dai, Linfeng Song, Haolin Liu, Zhenwen Liang, Dian Yu, Haitao Mi, Zhaopeng Tu, Rui Liu, Tong Zheng, Hongtu Zhu, and 1 others. 2025. Cde: Curiosity-driven exploration for efficient reinforcement learning in large language models. arXiv preprint arXiv:2509.09675. — [arXiv:2509.09675](https://arxiv.org/abs/2509.09675) find
  5. Tri Dao, Daniel Y. Fu, Stefano Ermon, Atri Rudra, and Christopher Ré. 2022. Flashattention: Fast and memory-efficient exact attention with io-awareness. Preprint, arXiv:2205.14135. find
  6. DeepSeek-AI, Daya Guo, 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, and 181 others. 2026. Deepseek-r1: Incentivizing reasoning capability in ll…
  7. Daniel Deutsch, Eleftheria Briakou, Isaac Rayburn Caswell, Mara Finkelstein, Rebecca Galor, Juraj Juraska, Geza Kovacs, Alison Lui, Ricardo Rei, Jason Riesa, and 1 others. 2025. Wmt24++: Expanding the language coverage of wmt24 to 55 languages & dialects. In Findings of the Association for Computati…
  8. Tianyu Dong, Bo Li, Jinsong Liu, Shaolin Zhu, and Deyi Xiong. 2025. Mlas-lora: language-aware parameters detection and lora-based knowledge transfer for multilingual machine translation. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers… find
  9. Zhaopeng Feng, Shaosheng Cao, Jiahan Ren, Jiayuan Su, Ruizhe Chen, Yan Zhang, Zhe Xu, Yao Hu, Jian Wu, and Zuozhu Liu. 2025a. Mt-r1-zero: Advancing llm-based machine translation via r1-zero-like reinforcement learning. Preprint, arXiv:2504.10160. find
  10. 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. Preprint, arXiv:2503.12123. find
  11. 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.
  12. Transactions of the Association for Computational Linguistics, 12:979–995. for Computational Linguistics: ACL 2024, pages 11628–11638, Bangkok, Thailand. Association for Computational Linguistics. find
  13. Junjie Hu, Hiroaki Hayashi, Kyunghyun Cho, and Graham Neubig. 2022. DEEP: DEnoising entity pre-training for neural machine translation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1753–1766, Dublin, Ireland. Association fo… find
  14. Jiacai Liu, Chaojie Wang, Chris Yuhao Liu, Liang Zeng, Rui Yan, Yiwen Sun, and Yang Liu. 2025. DAPO : Improving multi-step reasoning abilities of large language models with direct advantage-based policy optimization. In The Thirty-ninth Annual Conference on Neural Information Processing Systems. find
  15. Fanding Huang, Guanbo Huang, Xiao Fan, Yi He, Xiao Liang, Xiao Chen, Qinting Jiang, Faisal Nadeem Khan, Jingyan Jiang, and Zhi Wang. 2026. Semantic-space exploration and exploitation in rlvr for llm reasoning. Preprint, arXiv:2509.23808. find
  16. Nikita Moghe, Arnisa Fazla, Chantal Amrhein, Tom Kocmi, Mark Steedman, Alexandra Birch, Rico Sennrich, and Liane Guillou. 2025. Machine translation meta evaluation through translation accuracy challenge sets. Computational Linguistics, 51(1):73–137.
  17. Gautier Izacard, Mathilde Caron, Lucas Hosseini, Sebastian Riedel, Piotr Bojanowski, Armand Joulin, and Edouard Grave. 2021. Unsupervised dense information retrieval with contrastive learning.
  18. Leiyu Pan, Bojian Xiong, Lei Yang, Renren Jin, Shaowei Zhang, Yue Chen, Ling Shi, Jiang Zhou, Junru Wu, Zhen Wang, and 1 others. 2025a. Advancing large language models for tibetan with curated data and continual pre-training. arXiv preprint arXiv:2507.09205. — [arXiv:2507.09205](https://arxiv.org/abs/2507.09205) find
  19. Changjiang Jiang, Wenhui Dong, Zhonghao Zhang, Chenyang Si, Fengchang Yu, Wei Peng, Xinbin Yuan, Yifei Bi, Ming Zhao, Zian Zhou, and 1 others. 2025a. Ivy-fake: A unified explainable framework and benchmark for image and video aigc detection. arXiv preprint arXiv:2506.00979. — [arXiv:2506.00979](https://arxiv.org/abs/2506.00979) find
  20. Changjiang Jiang, Xinkuan Sha, Fengchang Yu, Jingjing Liu, Jian Liu, Mingqi Fang, Chenfeng Zhang, and Wei Lu. 2026. Fake-hr1: Rethinking reasoning of vision language model for synthetic image detection. In ICASSP. find
  21. Changjiang Jiang, Fengchang Yu, Haihua Chen, Wei Lu, and Jin Zeng. 2025b. Tabdsr: Decompose, sanitize, and reason for complex numerical reasoning in tabular data. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 3172–3196. find
  22. Renren Jin, Pengzhi Gao, Yuqi Ren, Zhuowen Han, Tongxuan Zhang, Wuwei Huang, Wei Liu, Jian Luan, and Deyi Xiong. 2025. Revisiting entropy in reinforcement learning for large reasoning models. arXiv preprint arXiv:2511.05993. find
  23. Urvashi Khandelwal, Angela Fan, Dan Jurafsky, Luke Zettlemoyer, and Mike Lewis. Nearest neighbor machine translation. In International Conference on Learning Representations. Nathan Lambert, Jacob Morrison, Valentina Pyatkin, Shengyi Huang, Hamish Ivison, Faeze Brahman, Lester James V. Miranda, Alis… — Tulu 3: Pushing Frontiers in Open Language Model Post-Training
  24. Tian Liang, Xing Wang, Mingming Yang, Yujiu Yang, Shuming Shi, and Zhaopeng Tu. 2024. Addressing entity translation problem via translation difficulty and context diversity. In Findings of the Association Leiyu Pan, Bojian Xiong, Lei Yang, Renren Jin, Shaowei Zhang, Yue Chen, Ling Shi, Jiang Zhou, J… find
  25. Maja Popović. 2015. chrF: character n-gram F-score for automatic MT evaluation. In Proceedings of the Tenth Workshop on Statistical Machine Translation, pages 392–395, Lisbon, Portugal. Association for Computational Linguistics.
  26. Qwen, :, 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, and 25 others. 2025. Qwen2.5 technical report. Preprint, arXiv:2412.15115. find
  27. Ricardo Rei, José G. C. de Souza, Duarte Alves, Chrysoula Zerva, Ana C Farinha, Taisiya Glushkova, Alon Lavie, Luisa Coheur, and André F. T. Martins. 2022. COMET-22: Unbabel-IST 2022 submission for the metrics shared task. In Proceedings of the Seventh Conference on Machine Translation (WMT), pages…
  28. Ricardo Rei, Nuno M. Guerreiro, Marcos Treviso, Luisa Coheur, Alon Lavie, and André Martins. 2023. The inside story: Towards better understanding of machine translation neural evaluation metrics. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Sh… find
  29. Matiss Rikters and Makoto Miwa. 2024. Entity-aware multi-task training helps rare word machine translation. In Proceedings of the 17th International Natural Language Generation Conference, pages 47–54, Tokyo, Japan. Association for Computational Linguistics. find
  30. John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. Preprint, arXiv:1707.06347. find
  31. 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.
  32. Guangming Sheng, Chi Zhang, Zilingfeng Ye, Xibin Wu, Wang Zhang, Ru Zhang, Yanghua Peng, Haibin Lin, and Chuan Wu. 2024. Hybridflow: A flexible and efficient rlhf framework. arXiv preprint arXiv: 2409.19256.
  33. Jiaan Wang, Fandong Meng, Yunlong Liang, and Jie Zhou. 2025a. Drt: Deep reasoning translation via long chain-of-thought. Preprint, arXiv:2412.17498. find
  34. Jiaan Wang, Fandong Meng, Yingxue Zhang, and Jie Zhou. 2025b. Retrieval-augmented machine translation with unstructured knowledge. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 5858–5871, Suzhou, China. Association for Computational Linguistics. find
  35. Jiaan Wang, Fandong Meng, and Jie Zhou. 2025c. Deeptrans: Deep reasoning translation via reinforcement learning. Preprint, arXiv:2504.10187.
  36. Xinwei Wu, Heng Liu, Xiaohu Zhao, Yuqi Ren, Linlong Xu, Longyue Wang, Deyi Xiong, Weihua Luo, and Kaifu Zhang. 2026. Finding the translation switch: Discovering and exploiting the task-initiation features in llms. arXiv preprint arXiv:2601.11019. — [arXiv:2601.11019](https://arxiv.org/abs/2601.11019) find
  37. Xinbin Yuan, Jian Zhang, Kaixin Li, Zhuoxuan Cai, Lujian Yao, Jie Chen, Enguang Wang, Qibin Hou, Jinwei Chen, Peng-Tao Jiang, and Bo Li. 2025. SE-GUI: Enhancing visual grounding for GUI agents via self-evolutionary reinforcement learning. In The Thirty-ninth Annual Conference on Neural Information P… find
  38. 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.
  39. Qiannian Zhao, Chen Yang, Jinhao Jing, Yunke Zhang, Xuhui Ren, Lu Yu, Shijie Zhang, and Hongzhi Yin. 2026. Know what you know: Metacognitive entropy calibration for verifiable rl reasoning. arXiv preprint arXiv:2602.22751. — [arXiv:2602.22751](https://arxiv.org/abs/2602.22751) find
  40. Yu Zhao, Huifeng Yin, Bo Zeng, Hao Wang, Tianqi Shi, Chenyang Lyu, Longyue Wang, Weihua Luo, and Kaifu Zhang. 2024a. Marco-o1: Towards open reasoning models for open-ended solutions. Preprint, arXiv:2411.14405. find
  41. Yuze Zhao, Jintao Huang, Jinghan Hu, Xingjun Wang, Yunlin Mao, Daoze Zhang, Zeyinzi Jiang, Zhikai Wu, Baole Ai, Ang Wang, Wenmeng Zhou, and Yingda Chen. 2024b. Swift:a scalable lightweight infrastructure for fine-tuning. Preprint, arXiv:2408.05517. — [arXiv:2408.05517](https://arxiv.org/abs/2408.05517) find
  42. 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. Preprint, arXiv:2507.18071.
  43. Jiang Zhou, Yunhao Wang, Xing Wu, Tinghao Yu, and Feng Zhang. 2026. Wrap++: Web discovery amplified pretraining. arXiv preprint arXiv:2604.06829. — [arXiv:2604.06829](https://arxiv.org/abs/2604.06829) find
  44. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, and 1 others. 2025. Qwen3 technical report. arXiv preprint arXiv:2505.09388.
  45. Lei Yang, Wei Bi, Chenxi Sun, Renren Jin, and Deyi Xiong. 2026. SOUP: Token-level Single-sample Mix-policy Reinforcement Learning for large language models. CoRR, abs/2601.21476. — [arXiv:2601.21476](https://arxiv.org/abs/2601.21476) find
  46. Binwei Yao, Ming Jiang, Tara Bobinac, Diyi Yang, and Junjie Hu. 2024. Benchmarking machine translation with cultural awareness. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 13078–13096, Miami, Florida, USA. Association for Computational Linguistics.
  47. Linhao Yu, Tianmeng Yang, Siyu Ding, Renren Jin, Naibin Gu, Xiangzhao Hao, Shuaiyi Nie, Deyi Xiong, Weichong Yin, Yu Sun, and 1 others. 2026. Knowrl: Boosting llm reasoning via reinforcement learning with minimal-sufficient knowledge guidance. arXiv preprint arXiv:2604.12627. — [arXiv:2604.12627](https://arxiv.org/abs/2604.12627) find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/zhou-2026-incentivizing-parametric-knowledge-reinforcement-learning/