Making Qwen3 Think in Korean with Reinforcement Learning
This work addresses the challenge of enhancing Korean reasoning alignment in language models, though it is incremental as it builds on existing fine-tuning and reinforcement learning methods.
The researchers tackled the problem of making the Qwen3 14B large language model think natively in Korean by developing a two-stage fine-tuning approach, which achieved stable learning and improved performance on advanced reasoning benchmarks like math and coding tasks while maintaining language proficiency.
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.