待翻譯：GRPO Beyond English: A Large-Scale Study of GRPO in Non-English and Multilingual Settings

AI 服務暫時不可用，以下為來源正文，待恢復後補全翻譯。

--> [Submitted on 13 Aug 2026] Title:GRPO Beyond English: A Large-Scale Study of GRPO in Non-English and Multilingual Settings View a PDF of the paper titled GRPO Beyond English: A Large-Scale Study of GRPO in Non-English and Multilingual Settings, by Konstantin Dobler and 4 other authors View PDF HTML (experimental) Abstract:Reinforcement Learning with Verifiable Rewards (RLVR), often optimized with Group Relative Policy Optimization (GRPO), has become a central recipe for improving the reasoning capabilities of pretrained language models but current studies remain heavily English-centric. We conduct a large-scale empirical study of multilingual and non-English GRPO across a wide range of base models, training languages, and different reasoning language rewards. We find that training to reason in the native language often leaves only a small gap to training for English reasoning. We further observe strong crosslingual transfer: training in one language often improves performance in many others. However, specific trends are highly model- and language-dependent. In some cases, training in a particular language induces severe regressions on out-of-domain capabilities in other languages. Our analysis shows that RLVR beyond English can provide broad crosslingual gains, but also requires broad evaluation to detect language-specific regressions. Subjects: Computation and Language (cs.CL); Machine Learning (cs.LG) Cite as: arXiv:2608.13698 [cs.CL] (or arXiv:2608.13698v1 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2608.13698 arXiv-issued DOI via DataCite (pending registration) Submission history From: Konstantin Dobler [view email] [v1] Thu, 13 Aug 2026 18:43:33 UTC (14,393 KB) Full-text links: Access Paper: View a PDF of the paper titled GRPO Beyond English: A Large-Scale Study of GRPO in Non-English and Multilingual Settings, by Konstantin Dobler and 4 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CL new | recent | 2026-08 Change to browse by: cs cs.LG References & Citations NASA ADS Google Scholar Semantic Scholar Loading... Data provided by: Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)