KORMo: Korean Open Reasoning Model for Everyone
It provides a transparent framework for developing synthetic data-driven fully open models in low-resource language settings, setting a reproducible precedent for future multilingual LLM research.
This work tackled the challenge of constructing a fully open bilingual large language model for Korean, predominantly using synthetic data, and resulted in KORMo-10B, a 10.8B-parameter model that achieves performance comparable to contemporary open-weight multilingual baselines across reasoning, knowledge, and instruction-following benchmarks.
This work presents the first large-scale investigation into constructing a fully open bilingual large language model (LLM) for a non-English language, specifically Korean, trained predominantly on synthetic data. We introduce KORMo-10B, a 10.8B-parameter model trained from scratch on a Korean-English corpus in which 68.74% of the Korean portion is synthetic. Through systematic experimentation, we demonstrate that synthetic data, when carefully curated with balanced linguistic coverage and diverse instruction styles, does not cause instability or degradation during large-scale pretraining. Furthermore, the model achieves performance comparable to that of contemporary open-weight multilingual baselines across a wide range of reasoning, knowledge, and instruction-following benchmarks. Our experiments reveal two key findings: (1) synthetic data can reliably sustain long-horizon pretraining without model collapse, and (2) bilingual instruction tuning enables near-native reasoning and discourse coherence in Korean. By fully releasing all components including data, code, training recipes, and logs, this work establishes a transparent framework for developing synthetic data-driven fully open models (FOMs) in low-resource settings and sets a reproducible precedent for future multilingual LLM research.