Mi:dm 2.0 Korea-centric Bilingual Language Models
Not on the map. Why?
Abstract (arXiv)
We introduce Mi:dm 2.0, a bilingual large language model (LLM) specifically engineered to advance Korea-centric AI. This model goes beyond Korean text processing by integrating the values, reasoning patterns, and commonsense knowledge inherent to Korean society, enabling nuanced understanding of cultural contexts, emotional subtleties, and real-world scenarios to generate reliable and culturally appropriate responses. To address limitations of existing LLMs, often caused by insufficient or low-quality Korean data and lack of cultural alignment, Mi:dm 2.0 emphasizes robust data quality through a comprehensive pipeline that includes proprietary data cleansing, high-quality synthetic data generation, strategic data mixing with curriculum learning, and a custom Korean-optimized tokenizer to improve efficiency and coverage. To realize this vision, we offer two complementary configurations: Mi:dm 2.0 Base (11.5B parameters), built with a depth-up scaling strategy for general-purpose use, and Mi:dm 2.0 Mini (2.3B parameters), optimized for resource-constrained environments and specialized tasks. Mi:dm 2.0 achieves state-of-the-art performance on Korean-specific benchmarks, with top-tier zero-shot results on KMMLU and strong internal evaluation results across language, humanities, and social science tasks. The Mi:dm 2.0 lineup is released under the MIT license to support extensive research and commercial use. By offering accessible and high-performance Korea-centric LLMs, KT aims to accelerate AI adoption across Korean industries, public services, and education, strengthen the Korean AI developer community, and lay the groundwork for the broader vision of K-intelligence. Our models are available at https://huggingface.co/K-intelligence. For technical inquiries, please contact [email protected].
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 44 of its 60 references that are in the map. First posted on arXiv 14 Jan 2026.
Builds on
44 of 60 references.
References · 44
- 2024The Llama 3 Herd of Modelscited by 14,192
- 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
- 2021Training Verifiers to Solve Math Word Problemscited by 9,743
- 2020Measuring Massive Multitask Language Understandingcited by 7,768
- 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 2,914
- 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,748
- 2020GLU Variants Improve Transformercited by 1,724
- 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,414
- 2023GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpointscited by 1,311
- 2024RULER: What's the Real Context Size of Your Long-Context Language Models?cited by 1,270
- 2023Instruction-Following Evaluation for Large Language Modelscited by 1,143
- 2024The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scalecited by 1,104
32 more
- 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
- 2024MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategiescited by 694
- 2024Phi-4 Technical Reportcited by 675
- 2023YaRN: Efficient Context Window Extension of Large Language Modelscited by 584
- 2019Improved Knowledge Distillation via Teacher Assistantcited by 567
- 2023XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Modelscited by 477
- 2024DataComp-LM: In search of the next generation of training sets for language modelscited by 381
- 2025OpenThoughts: Data Recipes for Reasoning Modelscited by 287
- 2024MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Casescited by 216
- 2023MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoningcited by 195
- 2024Arcee's MergeKit: A Toolkit for Merging Large Language Modelscited by 189
- 2023SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scalingcited by 172
- 2023MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoningcited by 155
- 2024Nemotron-CC: Transforming Common Crawl into a Refined Long-Horizon Pretraining Datasetcited by 153
- 2024Compact Language Models via Pruning and Knowledge Distillationcited by 142
- 2024How to Train Long-Context Language Models (Effectively)cited by 141
- 2024KMMLU: Measuring Massive Multitask Language Understanding in Koreancited by 91
- 2024LLM Pruning and Distillation in Practice: The Minitron Approachcited by 82
- 2023KoBBQ: Korean Bias Benchmark for Question Answeringcited by 71
- 2024KOR-Bench: Benchmarking Language Models on Knowledge-Orthogonal Reasoning Taskscited by 67
- 2024CLIcK: A Benchmark Dataset of Cultural and Linguistic Intelligence in Koreancited by 65
- 2024On the Diversity of Synthetic Data and its Impact on Training Large Language Modelscited by 56
- 2024Base of RoPE Bounds Context Lengthcited by 49
- 2023HAE-RAE Bench: Evaluation of Korean Knowledge in Language Modelscited by 47
- 2025Understand, Solve and Translate: Bridging the Multilingual Mathematical Reasoning Gapcited by 41
- 2024Needle in the Haystack for Memory Based Large Language Modelscited by 32
- 2024EXAONE 3.0 7.8B Instruction Tuned Language Modelcited by 20
- 2025Kanana: Compute-efficient Bilingual Language Modelscited by 19
- 2024Quality Matters: Evaluating Synthetic Data for Tool-Using LLMscited by 17
- 2025Social Bias Benchmark for Generation: A Comparison of Generation and QA-Based Evaluationscited by 14
- 2025RSafe: Incentivizing proactive reasoning to build robust and adaptive LLM safeguardscited by 14
- 2024Open Ko-LLM Leaderboard2: Bridging Foundational and Practical Evaluation for Korean LLMscited by 6
Built on by
Citing papers per year: 2026: 3.
3 papers.