CLJun 18, 2025

Thunder-LLM: Efficiently Adapting LLMs to Korean with Minimal Resources

arXiv:2506.21595v11 citations
Originality Incremental advance
AI Analysis

This addresses the issue of LLM underperformance in non-English languages like Korean for users needing cost-effective language adaptation, though it is incremental as it builds on existing methods for a specific domain.

The paper tackles the problem of adapting English-based large language models (LLMs) to Korean efficiently with minimal resources, resulting in Thunder-LLM models that achieve superior Korean performance compared to state-of-the-art models while using minimal data and computational resources.

Since state-of-the-art LLMs often underperform in languages other than English or Chinese, improving the capability of LLMs in new languages has become an essential task. Moreover, LLMs' entire end-to-end training process remains largely unknown to the public due to proprietary reasons, technical complexity, inconsistent documentation, and ethical considerations. The complete picture remains a closely guarded secret within the industry. This paper presents methods to adapt an existing English-based LLM to Korean in a low-budget scenario. We describe the entire end-to-end process: collecting Korean datasets, preprocessing the data, training the model, creating downstream benchmarks, and conducting evaluations. The evaluation results indicate that our method can effectively and cost-efficiently add new language capabilities to existing LLMs. Our new bilingual models, Thunder-LLM and Thunder-LLM-Ins, achieve superior Korean performance compared to state-of-the-art models while utilizing minimal data and computational resources. We share our comprehensive experience and make the code publicly available.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes