paper-with-me

Papers

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

2026-08-13 · Konstantin Dobler, Federico Scozzafava, Jonathan Janke, Mohamed Ali, Simon Lehnerer arxiv

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.

📄 PDF Abstract BibTeX arXiv:2608.13698

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Improving Cross-Lingual Factual Recall via Consistency-Driven Reinforcement Learning

2026-06-04 · Jonathan von Rad, Louis Arts, George Burgess, Eleftheria Kolokytha 외 arxiv

Large language models (LLMs) trained predominantly on English data encode substantial world knowledge, yet often fail to express it reliably in other languages, a phenomenon known as cross-lingual factual inconsistency. …

Reinforcement LearningContinual Pretraining

AMIR-GRPO: Inducing Implicit Preference Signals into GRPO

2026-01-07 · Amir Hossein Yari, Fajri Koto arxiv

Reinforcement learning has become the primary paradigm for aligning large language models (LLMs) on complex reasoning tasks, with group relative policy optimization (GRPO) widely used in large-scale post-training. Howeve…

Reinforcement LearningMathematical Reasoning

Typhoon-S: Minimal Open Post-Training for Sovereign Large Language Models

2026-01-26 · Kunat Pipatanakul, Pittawat Taveekitworachai arxiv

Large language models (LLMs) have progressed rapidly; however, most state-of-the-art models are trained and evaluated primarily in high-resource languages such as English and Chinese, and are often developed by a small n…

Legal Reasoning

Multi-Reward GRPO Fine-Tuning for De-biasing Large Language Models: A Study Based on Chinese-Context Discrimination Data

2025-11-08 · Deng Yixuan, Ji Xiaoqiang arxiv

Large Language Models (LLMs) often exhibit implicit biases and discriminatory tendencies that reflect underlying social stereotypes. While recent alignment techniques such as RLHF and DPO have mitigated some of these iss…

Cost of Reasoning in non-English Languages: A Case Study on Japanese

2026-07-11 · Yuu Jinnai arxiv

Reasoning Language Models (RLMs) achieve their strongest performance when they reason in English, the language for which reasoning-oriented training data is most abundant. However, reasoning trace is a clue for model int…