---
title: "x1: Learning to Think Adaptively Across Languages and Cultures"
description: "The authors build x1, a family of models derived from open-source reasoners, in two steps. 39 references, cited by 1 paper here."
authors: ["Yangfan Ye", "Xiaocheng Feng", "Xiachong Feng", "Yichong Huang", "Zekun Yuan", "Lei Huang", "Weitao Ma", "Qichen Hong", "Yunfei Lu", "Dandan Tu", "Bing Qin"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.712/"
doi: "10.18653/v1/2026.findings-acl.712"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/ye-2026-x1-learning-think-adaptively-across/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/ye-2026-x1-learning-think-adaptively-across/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/19/) / x1: Learning to Think Adaptively Across Languages and Cultures

# x1: Learning to Think Adaptively Across Languages and Cultures

**Authors:** [Yangfan Ye](https://md.research.elamur.ai/free/en/authors/yangfan-ye/), [Xiaocheng Feng](https://md.research.elamur.ai/free/en/authors/xiaocheng-feng/), [Xiachong Feng](https://md.research.elamur.ai/free/en/authors/xiachong-feng/), Yichong Huang, [Zekun Yuan](https://md.research.elamur.ai/free/en/authors/zekun-yuan/), [Lei Huang](https://md.research.elamur.ai/free/en/authors/lei-huang/), [Weitao Ma](https://md.research.elamur.ai/free/en/authors/weitao-ma/), [Qichen Hong](https://md.research.elamur.ai/free/en/authors/qichen-hong/), [Yunfei Lu](https://md.research.elamur.ai/free/en/authors/yunfei-lu/), [Dandan Tu](https://md.research.elamur.ai/free/en/authors/dandan-tu/) and [Bing Qin](https://md.research.elamur.ai/free/en/authors/bing-qin/) · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: ACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.findings-acl.712/) · [PDF](https://aclanthology.org/2026.findings-acl.712.pdf) · [DOI 10.18653/v1/2026.findings-acl.712](https://doi.org/10.18653/v1/2026.findings-acl.712) · [OpenAlex](https://openalex.org/W7166881175)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · 1 in our library, of the 149,439 papers whose bibliographies we read

## Summary
Most reasoning LLMs think mainly in one dominant language, usually English, even when a question is posed in another language or depends on a specific culture. This paper asks whether choosing the reasoning language for each instance can help. The authors build x1, a family of models derived from open-source reasoners, in two steps. First, the model learns to reason in an explicitly requested language by fine-tuning on its own reasoning traces, which it translates into 30 languages. Second, for each input it compares an English trajectory with a non-English one and learns to pick the language that yields the better response. The method adds no external knowledge, so any change in results comes from the choice of reasoning language alone. Experiments on multilingual math and culturally grounded questions show benefits from this adaptive choice. Larger models show smaller cross-lingual gaps in math, but reasoning in a culture-associated language still improves cultural knowledge recall. The authors conclude that language choice is a functional part of reasoning, which matters for building globally competent models.

## Key points
- **Motivating analysis:** for Qwen3-4B on MGSM, roughly 3–9% of instances (depending on the language) are solved by non-English reasoning but not by English reasoning.
- **Step 1 (multilingual reasoning):**
  - 200 seed questions are sampled from Flan_v2, and the model self-translates its reasoning traces into 30 languages.
  - Poor translations are filtered out using COMET scores.
  - Training uses templated tags such as `<Arabic_start>`, producing a "surface-level" multilingual reasoner, M_surface.
- **Step 2 (adaptive reasoning):**
  - Paired English and non-English trajectories for the same input provide self-generated contrastive signals for choosing the language.
  - Training uses LoRA adaptation, with source data covering 10 languages and 45 cultural backgrounds.
- **Extra gains:** applying DPO with the advantageous-language trajectory as the preferred sample further improves multilingual math results.
- **Limitations:** each instance has only two candidate languages (English plus one non-English language), and cultural tasks are evaluated with an LLM-as-a-Judge. Code is available at github.com/YYF-Tommy/x1-adaptive-multilingual-reasoning.

*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

- [Harbin Institute of Technology](https://md.research.elamur.ai/free/en/universities/harbin-institute-of-technology/) — University, Harbin, China · 185 works · 29,140 citations
- [University of Hong Kong](https://md.research.elamur.ai/free/en/universities/university-of-hong-kong/) — University, Pok Fu Lam, China · 118 works · 13,496 citations
- [Peng Cheng Laboratory](https://md.research.elamur.ai/free/en/labs/peng-cheng-laboratory/) — Research institute, Shenzhen, China · 47 works · 2,699 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works

🧭 Topics (1): [🧮 Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/) · 1,685 works

## Cite

Cite as: Yangfan Ye, Xiaocheng Feng, Xiachong Feng, Yichong Huang, Zekun Yuan, Lei Huang, Weitao Ma, Qichen Hong, Yunfei Lu, Dandan Tu and Bing Qin. 2026. x1: Learning to Think Adaptively Across Languages and Cultures. Findings of the Association for Computational Linguistics: ACL 2026.

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

```bibtex
@inproceedings{ye2026x1,
  title = {{x1: Learning to Think Adaptively Across Languages and Cultures}},
  author = {Yangfan Ye, Xiaocheng Feng, Xiachong Feng, Yichong Huang, Zekun Yuan, Lei Huang, Weitao Ma, Qichen Hong, Yunfei Lu, Dandan Tu and Bing Qin},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.712},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.712}
}
```

- [← previous X-NLP at SemEval-2026 Task 12: Prompting LLMs for Abductive Event Reasoning](https://md.research.elamur.ai/free/en/papers/mattie-2026-x-nlp-semeval-2026-task/)
- [next → XQ-MEval: A Dataset with Cross-lingual Parallel Quality for Benchmarking Translation Metrics](https://md.research.elamur.ai/free/en/papers/liu-2026-xq-meval-dataset-cross-lingual/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/19/)

## References

39 references, 24 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Bradley Brown, Jordan Juravsky, Ryan Ehrlich, Ronald Clark, Quoc V Le, Christopher Ré, and Azalia Mirhoseini. 2024. [Large language monkeys: Scaling inference compute with repeated sampling](https://md.research.elamur.ai/free/en/papers/brown-2024-large-language-monkeys-scaling-inference/). arXiv preprint arXiv:2407.21787.
2. Nuo Chen, Zinan Zheng, Ning Wu, Ming Gong, Dongmei Zhang, and Jia Li. 2023. [Breaking language barriers in multilingual mathematical reasoning: Insights and observations](https://md.research.elamur.ai/free/en/papers/chen-2024-breaking-language-barriers-multilingual-mathematical/). arXiv preprint arXiv:2310.20246.
3. Yu Ying Chiu, Liwei Jiang, Bill Yuchen Lin, Chan Young Park, Shuyue Stella Li, Sahithya Ravi, Mehar Bhatia, Maria Antoniak, Yulia Tsvetkov, Vered Shwartz, and Yejin Choi. 2025. [CulturalBench: A robust, diverse and challenging benchmark for measuring LMs’ cultural knowledge through human-AI red-teami…](https://md.research.elamur.ai/free/en/papers/chiu-2025-culturalbench-robust-diverse-challenging-benchmark/)
4. Yuchun Fan, Yongyu Mu, Yilin Wang, Lei Huang, Junhao Ruan, Bei Li, Tong Xiao, Shujian Huang, Xiaocheng Feng, and Jingbo Zhu. 2025. [Slam: Towards efficient multilingual reasoning via selective language alignment](https://md.research.elamur.ai/free/en/papers/fan-2025-slam-efficient-multilingual-reasoning-selective/). arXiv preprint arXiv:2501.03681.
5. Cliff Goddard. 2003. Thinking across languages and cultures: Six dimensions of variation. Cognitive linguistics, 14(2/3):109–140. [find](https://scholar.google.com/scholar?q=Cliff+Goddard%2E+2003%2E+Thinking+across+languages+and+cultures%3A+Six+dimensions+of+variation%2E+Cognitive+linguistics%2C+14%282%2F3%29%3A109%E2%80%93140%2E)
6. Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, et al. 2025. [Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning](https://md.research.elamur.ai/free/en/papers/deepseek-ai-2025-deepseek-r1-incentivizing-reasoning-capability/). arXiv preprint arXiv:2501.12948.
7. Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al. 2022. [Lora: Low-rank adaptation of large language models](https://md.research.elamur.ai/free/en/papers/hu-2021-lora-low-rank-adaptation-large/). ICLR, 1(2):3.
8. Aaron Jaech, Adam Kalai, Adam Lerer, Adam Richardson, Ahmed El-Kishky, Aiden Low, Alec Helyar, Aleksander Madry, Alex Beutel, Alex Carney, et al. 2024. [Openai o1 system card](https://md.research.elamur.ai/free/en/papers/openai-2024-openai-o1-system-card/). arXiv:2412.16720. arXiv preprint model is secretly a reward model. Advances in neural information processing systems, 36:5372…
9. Hyunwoo Ko, Guijin Son, and Dasol Choi. 2025. Understand, solve and translate: Bridging the multilingual mathematical reasoning gap. arXiv preprint arXiv:2501.02448. [find](https://scholar.google.com/scholar?q=Hyunwoo+Ko%2C+Guijin+Son%2C+and+Dasol+Choi%2E+2025%2E+Understand%2C+solve+and+translate%3A+Bridging+the+multilingual+mathematical+reasoning+gap%2E+arXiv+preprint+arXiv%3A2501%2E02448%2E)
10. Leonardo Ranaldi, Barry Haddow, and Alexandra Birch. 2025. When natural language is not enough: The limits of in-context learning demonstrations in multilingual reasoning. In Findings of the Association for Computational Linguistics: NAACL 2025, pages 7369–7396. [find](https://scholar.google.com/scholar?q=Leonardo+Ranaldi%2C+Barry+Haddow%2C+and+Alexandra+Birch%2E+2025%2E+When+natural+language+is+not+enough%3A+The+limits+of+in%2Dcontext+learning+demonstrations+in+multilingual+reasoning%2E+In+Findings+of+the+Associati)
11. Grgur Kovač, Masataka Sawayama, Rémy Portelas, Cédric Colas, Peter Ford Dominey, and Pierre-Yves Oudeyer. 2023. Large language models as superpositions of cultural perspectives. arXiv preprint arXiv:2307.07870. — [arXiv:2307.07870](https://arxiv.org/abs/2307.07870) [find](https://scholar.google.com/scholar?q=Grgur+Kovac%CC%8C%2C+Masataka+Sawayama%2C+R%C3%A9my+Portelas%2C+C%C3%A9dric+Colas%2C+Peter+Ford+Dominey%2C+and+Pierre%2DYves+Oudeyer%2E+2023%2E+Large+language+models+as+superpositions+of+cultural+perspectives%2E+arXiv+preprint+arXiv%3A)
12. Zoltan Kovecses. 2006. Language, mind, and culture: A practical introduction. Oxford University Press. [find](https://scholar.google.com/scholar?q=Zoltan+Kovecses%2E+2006%2E+Language%2C+mind%2C+and+culture%3A+A+practical+introduction%2E+Oxford+University+Press%2E)
13. Huiyuan Lai and Malvina Nissim. 2024. [mCoT: Multilingual instruction tuning for reasoning consistency in language models](https://md.research.elamur.ai/free/en/papers/lai-2024-mcot-multilingual-instruction-tuning-reasoning/). In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 12012– 12026, Bangkok, Thailand. Association for Computa…
14. Chen Cecilia Liu, Fajri Koto, Timothy Baldwin, and Iryna Gurevych. 2024. [Are multilingual llms culturally-diverse reasoners? an investigation into multicultural proverbs and sayings](https://md.research.elamur.ai/free/en/papers/liu-2023-multilingual-llms-culturally-diverse-reasoners/). In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics:…
15. Hongyuan Lu, Zixuan Li, and Wai Lam. 2024. Dictionary insertion prompting for multilingual reasoning on multilingual large language models. arXiv preprint arXiv:2411.01141. [find](https://scholar.google.com/scholar?q=Hongyuan+Lu%2C+Zixuan+Li%2C+and+Wai+Lam%2E+2024%2E+Dictionary+insertion+prompting+for+multilingual+reasoning+on+multilingual+large+language+models%2E+arXiv+preprint+arXiv%3A2411%2E01141%2E)
16. Tuan-Phong Nguyen, Simon Razniewski, Aparna Varde, and Gerhard Weikum. 2023. [Extracting cultural commonsense knowledge at scale](https://md.research.elamur.ai/free/en/papers/nguyen-2022-extracting-cultural-commonsense-knowledge-scale/). In Proceedings of the ACM web conference 2023, pages 1907–1917.
17. Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al. 2022. [Training language models to follow instructions with human feedback](https://md.research.elamur.ai/free/en/papers/ouyang-2022-training-language-models-follow-instructions/). Advances in neural information processing systems, 35:27730–27744.
18. Shramay Palta and Rachel Rudinger. 2023. [FORK: A bite-sized test set for probing culinary cultural biases in commonsense reasoning models](https://md.research.elamur.ai/free/en/papers/palta-2023-fork-bite-sized-test-set/). In Findings of the Association for Computational Linguistics: ACL 2023, pages 9952–9962, Toronto, Canada. Association for Computational Linguistics.
19. Libo Qin, Qiguang Chen, Fuxuan Wei, Shijue Huang, and Wanxiang Che. 2023. [Cross-lingual prompting: Improving zero-shot chain-of-thought reasoning across languages](https://md.research.elamur.ai/free/en/papers/qin-2023-cross-lingual-prompting-improving-zero/). arXiv preprint arXiv:2310.14799.
20. Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D Manning, Stefano Ermon, and Chelsea Finn. 2023. Direct preference optimization: Your language Abhinav Sukumar Rao, Aditi Khandelwal, Kumar Tanmay, Utkarsh Agarwal, and Monojit Choudhury. 2023. Ethical reasoning over moral alignment: A case… [find](https://scholar.google.com/scholar?q=Rafael+Rafailov%2C+Archit+Sharma%2C+Eric+Mitchell%2C+Christopher+D+Manning%2C+Stefano+Ermon%2C+and+Chelsea+Finn%2E+2023%2E+Direct+preference+optimization%3A+Your+language+Abhinav+Sukumar+Rao%2C+Aditi+Khandelwal%2C+Kumar+)
21. Ricardo Rei, Nuno M Guerreiro, Daan Van Stigt, Marcos Treviso, Luísa Coheur, José GC de Souza, André FT Martins, et al. 2023. [Scaling up cometkiwi: Unbabel-ist 2023 submission for the quality estimation shared task](https://md.research.elamur.ai/free/en/papers/rei-2023-scaling-up-cometkiwi-unbabel-ist/). In Proceedings of the Eighth Conference on Machine Translation, pages 841–848.
22. 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](https://md.research.elamur.ai/free/en/papers/she-2024-mapo-advancing-multilingual-reasoning-through/). In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long…
23. Freda Shi, Mirac Suzgun, Markus Freitag, Xuezhi Wang, Suraj Srivats, Soroush Vosoughi, Hyung Won Chung, Yi Tay, Sebastian Ruder, Denny Zhou, et al. 2022. [Language models are multilingual chain-of-thought reasoners](https://md.research.elamur.ai/free/en/papers/shi-2022-language-models-multilingual-chain-thought/). arXiv preprint arXiv:2210.03057.
24. Weiyan Shi, Ryan Li, Yutong Zhang, Caleb Ziems, Raya Horesh, Rogério Abreu de Paula, Diyi Yang, et al. 2024. [Culturebank: An online community-driven knowledge base towards culturally aware language technologies](https://md.research.elamur.ai/free/en/papers/shi-2024-culturebank-online-community-driven-knowledge/). arXiv preprint arXiv:2404.15238.
25. Charlie Snell, Jaehoon Lee, Kelvin Xu, and Aviral Kumar. 2024. [Scaling llm test-time compute optimally can be more effective than scaling model parameters](https://md.research.elamur.ai/free/en/papers/snell-2024-scaling-llm-test-time-compute/), 2024. URL https://arxiv.org/abs/2408.03314, 20. [↗](https://arxiv.org/abs/2408.03314)
26. Guijin Son, Jiwoo Hong, Hyunwoo Ko, and James Thorne. 2025. [Linguistic generalizability of test-time scaling in mathematical reasoning](https://md.research.elamur.ai/free/en/papers/son-2025-linguistic-generalizability-test-time-scaling/). arXiv preprint arXiv:2502.17407.
27. Weixuan Wang, Minghao Wu, Barry Haddow, and Alexandra Birch. 2025. Demystifying multilingual chain-of-thought in process reward modeling. arXiv preprint arXiv:2502.12663. — [arXiv:2502.12663](https://arxiv.org/abs/2502.12663) [find](https://scholar.google.com/scholar?q=Weixuan+Wang%2C+Minghao+Wu%2C+Barry+Haddow%2C+and+Alexandra+Birch%2E+2025%2E+Demystifying+multilingual+chain%2Dof%2Dthought+in+process+reward+modeling%2E+arXiv+preprint+arXiv%3A2502%2E12663%2E+%E2%80%94+%5BarXiv%3A2502%2E12663%5D%28https%3A%2F%2F)
28. Wenxuan Wang, Wenxiang Jiao, Jingyuan Huang, Ruyi Dai, Jen-tse Huang, Zhaopeng Tu, and Michael Lyu. 2024. [Not all countries celebrate thanksgiving: On the cultural dominance in large language models](https://md.research.elamur.ai/free/en/papers/wang-2024-not-all-countries-celebrate-thanksgiving/). In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1…
29. Jason Wei, Maarten Bosma, Vincent Y Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, Andrew M Dai, and Quoc V Le. 2021. [Finetuned language models are zero-shot learners](https://md.research.elamur.ai/free/en/papers/wei-2021-finetuned-language-models-zero-shot/). arXiv preprint arXiv:2109.01652.
30. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al. 2022. [Chain-of-thought prompting elicits reasoning in large language models](https://md.research.elamur.ai/free/en/papers/wei-2022-chain-thought-prompting-elicits-reasoning/). Advances in Neural Information Processing Systems, 35:24824–24837.
31. Ludwig Wittgenstein. 2023. philosophicus. [find](https://scholar.google.com/scholar?q=Ludwig+Wittgenstein%2E+2023%2E+philosophicus%2E)
32. Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric Xing, et al. 2023. [Judging llm-as-a-judge with mt-bench and chatbot arena](https://md.research.elamur.ai/free/en/papers/zheng-2023-judging-llm-judge-mt-bench/). Advances in neural information processing systems, 36:46595–46623.
33. Wenhao Zhu, Shujian Huang, Fei Yuan, Cheng Chen, Jiajun Chen, and Alexandra Birch. 2024. The power of question translation training in multilingual reasoning: Broadened scope and deepened insights. arXiv preprint arXiv:2405.01345. — [arXiv:2405.01345](https://arxiv.org/abs/2405.01345) [find](https://scholar.google.com/scholar?q=Wenhao+Zhu%2C+Shujian+Huang%2C+Fei+Yuan%2C+Cheng+Chen%2C+Jiajun+Chen%2C+and+Alexandra+Birch%2E+2024%2E+The+power+of+question+translation+training+in+multilingual+reasoning%3A+Broadened+scope+and+deepened+insights%2E+ar)
34. Tractatus logico-An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, et al. 2025. [Qwen3 technical report](https://md.research.elamur.ai/free/en/papers/yang-2025-qwen3-technical-report/). arXiv preprint arXiv:2505.09388.
35. Yangfan Ye, Xiachong Feng, Xiaocheng Feng, Weitao Ma, Libo Qin, Dongliang Xu, Qing Yang, Hongtao Liu, and Bing Qin. 2024a. GlobeSumm: A challenging benchmark towards unifying multi-lingual, cross-lingual and multi-document news summarization. In Proceedings of the 2024 Conference on Empirical Method… [find](https://scholar.google.com/scholar?q=Yangfan+Ye%2C+Xiachong+Feng%2C+Xiaocheng+Feng%2C+Weitao+Ma%2C+Libo+Qin%2C+Dongliang+Xu%2C+Qing+Yang%2C+Hongtao+Liu%2C+and+Bing+Qin%2E+2024a%2E+GlobeSumm%3A+A+challenging+benchmark+towards+unifying+multi%2Dlingual%2C+cross%2Dling)
36. Yangfan Ye, Xiaocheng Feng, Xiachong Feng, Lei Huang, Weitao Ma, Qichen Hong, Yunfei Lu, Duyu Tang, Dandan Tu, and Bing Qin. 2025a. Langgps: Language separability guided data pre-selection for joint multilingual instruction tuning. arXiv preprint arXiv:2511.10229. — [arXiv:2511.10229](https://arxiv.org/abs/2511.10229) [find](https://scholar.google.com/scholar?q=Yangfan+Ye%2C+Xiaocheng+Feng%2C+Xiachong+Feng%2C+Lei+Huang%2C+Weitao+Ma%2C+Qichen+Hong%2C+Yunfei+Lu%2C+Duyu+Tang%2C+Dandan+Tu%2C+and+Bing+Qin%2E+2025a%2E+Langgps%3A+Language+separability+guided+data+pre%2Dselection+for+joint+m)
37. Yangfan Ye, Xiaocheng Feng, Xiachong Feng, Libo Qin, Yichong Huang, Lei Huang, Weitao Ma, Qichen Hong, Zhirui Zhang, Yunfei Lu, et al. 2024b. Exploring cross-lingual latent transplantation: Mutual opportunities and open challenges. arXiv preprint arXiv:2412.12686. — [arXiv:2412.12686](https://arxiv.org/abs/2412.12686) [find](https://scholar.google.com/scholar?q=Yangfan+Ye%2C+Xiaocheng+Feng%2C+Xiachong+Feng%2C+Libo+Qin%2C+Yichong+Huang%2C+Lei+Huang%2C+Weitao+Ma%2C+Qichen+Hong%2C+Zhirui+Zhang%2C+Yunfei+Lu%2C+et+al%2E+2024b%2E+Exploring+cross%2Dlingual+latent+transplantation%3A+Mutual+opp)
38. Yangfan Ye, Xiaocheng Feng, Zekun Yuan, Xiachong Feng, Libo Qin, Lei Huang, Weitao Ma, Yichong Huang, Zhirui Zhang, Yunfei Lu, Xiaohui Yan, Duyu Tang, Dandan Tu, and Bing Qin. 2025b. CC-tuning: A cross-lingual connection mechanism for improving joint multilingual supervised fine-tuning. In Proceedin… [find](https://scholar.google.com/scholar?q=Yangfan+Ye%2C+Xiaocheng+Feng%2C+Zekun+Yuan%2C+Xiachong+Feng%2C+Libo+Qin%2C+Lei+Huang%2C+Weitao+Ma%2C+Yichong+Huang%2C+Zhirui+Zhang%2C+Yunfei+Lu%2C+Xiaohui+Yan%2C+Duyu+Tang%2C+Dandan+Tu%2C+and+Bing+Qin%2E+2025b%2E+CC%2Dtuning%3A+A+cros)
39. Zheng-Xin Yong, M Farid Adilazuarda, Jonibek Mansurov, Ruochen Zhang, Niklas Muennighoff, Carsten Eickhoff, Genta Indra Winata, Julia Kreutzer, Stephen H Bach, and Alham Fikri Aji. 2025. Crosslingual reasoning through test-time scaling. arXiv preprint arXiv:2505.05408. — [arXiv:2505.05408](https://arxiv.org/abs/2505.05408) [find](https://scholar.google.com/scholar?q=Zheng%2DXin+Yong%2C+M+Farid+Adilazuarda%2C+Jonibek+Mansurov%2C+Ruochen+Zhang%2C+Niklas+Muennighoff%2C+Carsten+Eickhoff%2C+Genta+Indra+Winata%2C+Julia+Kreutzer%2C+Stephen+H+Bach%2C+and+Alham+Fikri+Aji%2E+2025%2E+Crosslingual+)

*Updated 2 November 2026*