Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2601.05459 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909985561116672 |
|---|---|
| author | Kim, Hongjin Lee, Jaewook Lee, Kiyoung Shin, Jong-hun Lim, Soojong Kwon, Oh-Woog |
| author_facet | Kim, Hongjin Lee, Jaewook Lee, Kiyoung Shin, Jong-hun Lim, Soojong Kwon, Oh-Woog |
| contents | Large Language Models (LLMs) demonstrate strong reasoning and self-correction abilities in high-resource languages like English, but their performance remains limited in low-resource languages such as Korean. In this study, we investigate whether reinforcement learning (RL) can enhance Korean reasoning abilities to a degree comparable to English. Our findings reveal that RL alone yields limited improvements when applied to models lacking inherent Korean reasoning capabilities. To address this, we explore several fine-tuning strategies and show that aligning the model's internal reasoning processes with Korean inputs-particularly by tuning Korean-specific neurons in early layers-is key to unlocking RL's effectiveness. We introduce a self-correction code-switching dataset to facilitate this alignment and observe significant performance gains in both mathematical reasoning and self-correction tasks. Ultimately, we conclude that the crucial factor in multilingual reasoning enhancement is not injecting new linguistic knowledge, but effectively eliciting and aligning existing reasoning capabilities. Our study provides a new perspective on how internal translation and neuron-level tuning contribute to multilingual reasoning alignment in LLMs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_05459 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Do LLMs Need Inherent Reasoning Before Reinforcement Learning? A Study in Korean Self-Correction Kim, Hongjin Lee, Jaewook Lee, Kiyoung Shin, Jong-hun Lim, Soojong Kwon, Oh-Woog Computation and Language Artificial Intelligence Large Language Models (LLMs) demonstrate strong reasoning and self-correction abilities in high-resource languages like English, but their performance remains limited in low-resource languages such as Korean. In this study, we investigate whether reinforcement learning (RL) can enhance Korean reasoning abilities to a degree comparable to English. Our findings reveal that RL alone yields limited improvements when applied to models lacking inherent Korean reasoning capabilities. To address this, we explore several fine-tuning strategies and show that aligning the model's internal reasoning processes with Korean inputs-particularly by tuning Korean-specific neurons in early layers-is key to unlocking RL's effectiveness. We introduce a self-correction code-switching dataset to facilitate this alignment and observe significant performance gains in both mathematical reasoning and self-correction tasks. Ultimately, we conclude that the crucial factor in multilingual reasoning enhancement is not injecting new linguistic knowledge, but effectively eliciting and aligning existing reasoning capabilities. Our study provides a new perspective on how internal translation and neuron-level tuning contribute to multilingual reasoning alignment in LLMs. |
| title | Do LLMs Need Inherent Reasoning Before Reinforcement Learning? A Study in Korean Self-Correction |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2601.05459 |