Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.09066 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917203050233856 |
|---|---|
| author | Shin, Donghoon Lee, Sejung Bae, Soonmin Ryu, Hwijung Ok, Changwon Jung, Hoyoun Ji, Hyesung Lim, Jeehyun Lee, Jehoon Han, Ji-Eun Baik, Jisoo Kim, Mihyeon Chung, Riwoo Lee, Seongmin Park, Wonjae Heo, Yoonseok Seo, Youngkyung Won, Seyoun Kim, Boeun Heo, Cheolhun Lee, Eunkyeong Lee, Honghee Ju, Hyeongju Seo, Hyeontae Shim, Jeongyong Lee, Jisoo Koh, Junseok Kim, Junwoo Lee, Minho Kang, Minji Kim, Minju Nam, Sangha Park, Seongheum Kim, Taehyeong Ahn, Euijai Jeung, Hong Seok Shin, Jisu Kim, Jiyeon Song, Seonyeong Kong, Seung Hyun Hong, Sukjin Yun, Taeyang Kim, Yu-Seon Lee, A-Hyun Lee, Chae-Jeong Yu, Hye-Won Ahn, Ji-Hyun Kim, Song-Yeon Jung, Sun-Woo Kim, Eunju Ha, Eunji Baek, Jinwoo Lee, Yun-ji Park, Wanjin Kim, Jeong Yeop Kim, Eun Mi Park, Hyoung Jun Yoon, Jung Won Noh, Min Sung Oh, Myung Gyo Lee, Wongyoung Park, Yun Jin Kwon, Young S. Kim, Hyun Keun Lee, Jieun Park, YeoJoo |
| author_facet | Shin, Donghoon Lee, Sejung Bae, Soonmin Ryu, Hwijung Ok, Changwon Jung, Hoyoun Ji, Hyesung Lim, Jeehyun Lee, Jehoon Han, Ji-Eun Baik, Jisoo Kim, Mihyeon Chung, Riwoo Lee, Seongmin Park, Wonjae Heo, Yoonseok Seo, Youngkyung Won, Seyoun Kim, Boeun Heo, Cheolhun Lee, Eunkyeong Lee, Honghee Ju, Hyeongju Seo, Hyeontae Shim, Jeongyong Lee, Jisoo Koh, Junseok Kim, Junwoo Lee, Minho Kang, Minji Kim, Minju Nam, Sangha Park, Seongheum Kim, Taehyeong Ahn, Euijai Jeung, Hong Seok Shin, Jisu Kim, Jiyeon Song, Seonyeong Kong, Seung Hyun Hong, Sukjin Yun, Taeyang Kim, Yu-Seon Lee, A-Hyun Lee, Chae-Jeong Yu, Hye-Won Ahn, Ji-Hyun Kim, Song-Yeon Jung, Sun-Woo Kim, Eunju Ha, Eunji Baek, Jinwoo Lee, Yun-ji Park, Wanjin Kim, Jeong Yeop Kim, Eun Mi Park, Hyoung Jun Yoon, Jung Won Noh, Min Sung Oh, Myung Gyo Lee, Wongyoung Park, Yun Jin Kwon, Young S. Kim, Hyun Keun Lee, Jieun Park, YeoJoo |
| contents | 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 midm-llm@kt.com. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_09066 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Mi:dm 2.0 Korea-centric Bilingual Language Models Shin, Donghoon Lee, Sejung Bae, Soonmin Ryu, Hwijung Ok, Changwon Jung, Hoyoun Ji, Hyesung Lim, Jeehyun Lee, Jehoon Han, Ji-Eun Baik, Jisoo Kim, Mihyeon Chung, Riwoo Lee, Seongmin Park, Wonjae Heo, Yoonseok Seo, Youngkyung Won, Seyoun Kim, Boeun Heo, Cheolhun Lee, Eunkyeong Lee, Honghee Ju, Hyeongju Seo, Hyeontae Shim, Jeongyong Lee, Jisoo Koh, Junseok Kim, Junwoo Lee, Minho Kang, Minji Kim, Minju Nam, Sangha Park, Seongheum Kim, Taehyeong Ahn, Euijai Jeung, Hong Seok Shin, Jisu Kim, Jiyeon Song, Seonyeong Kong, Seung Hyun Hong, Sukjin Yun, Taeyang Kim, Yu-Seon Lee, A-Hyun Lee, Chae-Jeong Yu, Hye-Won Ahn, Ji-Hyun Kim, Song-Yeon Jung, Sun-Woo Kim, Eunju Ha, Eunji Baek, Jinwoo Lee, Yun-ji Park, Wanjin Kim, Jeong Yeop Kim, Eun Mi Park, Hyoung Jun Yoon, Jung Won Noh, Min Sung Oh, Myung Gyo Lee, Wongyoung Park, Yun Jin Kwon, Young S. Kim, Hyun Keun Lee, Jieun Park, YeoJoo Computation and Language Artificial Intelligence 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 midm-llm@kt.com. |
| title | Mi:dm 2.0 Korea-centric Bilingual Language Models |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2601.09066 |