# Making Qwen3 Think in Korean with Reinforcement Learning

arXiv: https://arxiv.org/abs/2508.10355 · HTML: https://mlsanity.com/paper/2508.10355/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning.
- Builds on 8 of its 14 references that are in the map.
- First posted on arXiv 14 Aug 2025.

## Placed in

- LLM reasoning / [Reinforcement learning for reasoning](https://mlsanity.com/lr/reinforcement-learning-for-reasoning/)

## Builds on (most cited first, 8 of 8)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [Understanding R1-Zero-Like Training: A Critical Perspective](https://mlsanity.com/paper/2503.20783/) (2025)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [Smoothie-Qwen: Post-Hoc Smoothing to Reduce Language Bias in Multilingual LLMs](https://mlsanity.com/paper/2507.05686/) (2025)

## Built on by (most cited first, 5 of 5)

- [Think Natively: Unlocking Multilingual Reasoning with Consistency-Enhanced Reinforcement Learning](https://mlsanity.com/paper/2510.07300/) (2025)
- [Why Do Multilingual Reasoning Gaps Emerge in Reasoning Language Models?](https://mlsanity.com/paper/2510.27269/) (2025)
- [TAPO: Translation Augmented Policy Optimization for Multilingual Mathematical Reasoning](https://mlsanity.com/paper/2603.25419/) (2026)
- [Entropy-KL Divergence-based Token Masking: A Novel Approach for Selective Fine-tuning of Large Language Models](https://mlsanity.com/paper/2605.29303/) (2026)
- [Building Multilingual Bridges: Data Mixing as the Pillar of Generalization for In-Language Reasoning](https://mlsanity.com/paper/2609.10445/) (2026)

## Abstract (arXiv)

We present a two-stage fine-tuning approach to make the large language model Qwen3 14B "think" natively in Korean. In the first stage, supervised fine-tuning (SFT) on a high-quality Korean reasoning dataset establishes a strong foundation in Korean logical reasoning, yielding notable improvements in Korean-language tasks and even some gains in general reasoning ability. In the second stage, we employ reinforcement learning with a customized Group Relative Policy Optimization (GRPO) algorithm to further enhance both Korean reasoning alignment and overall problem-solving performance. We address critical stability challenges in GRPO training - such as reward hacking and policy collapse - by introducing an oracle judge model that calibrates the reward signal. Our approach achieves stable learning (avoiding the collapse observed in naive GRPO) and leads to steady, incremental performance gains. The final RL-tuned model demonstrates substantially improved results on advanced reasoning benchmarks (particularly math and coding tasks) while maintaining knowledge and language proficiency, successfully conducting its internal chain-of-thought entirely in Korean.