SEA-LION: Southeast Asian Languages in One Network
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915585757020160 |
|---|---|
| author | Ng, Raymond Nguyen, Thanh Ngan Huang, Yuli Tai, Ngee Chia Leong, Wai Yi Leong, Wei Qi Yong, Xianbin Ngui, Jian Gang Susanto, Yosephine Cheng, Nicholas Rengarajan, Hamsawardhini Limkonchotiwat, Peerat Hulagadri, Adithya Venkatadri Teng, Kok Wai Tong, Yeo Yeow Siow, Bryan Teo, Wei Yi Lau, Wayne Tan, Choon Meng Ong, Brandon Ong, Zhi Hao Montalan, Jann Railey Chan, Adwin Antonyrex, Sajeban Lee, Ren Choa, Esther Tat-Wee, David Ong Liu, Bing Jie Darius Tjhi, William Chandra Cambria, Erik Teo, Leslie |
| author_facet | Ng, Raymond Nguyen, Thanh Ngan Huang, Yuli Tai, Ngee Chia Leong, Wai Yi Leong, Wei Qi Yong, Xianbin Ngui, Jian Gang Susanto, Yosephine Cheng, Nicholas Rengarajan, Hamsawardhini Limkonchotiwat, Peerat Hulagadri, Adithya Venkatadri Teng, Kok Wai Tong, Yeo Yeow Siow, Bryan Teo, Wei Yi Lau, Wayne Tan, Choon Meng Ong, Brandon Ong, Zhi Hao Montalan, Jann Railey Chan, Adwin Antonyrex, Sajeban Lee, Ren Choa, Esther Tat-Wee, David Ong Liu, Bing Jie Darius Tjhi, William Chandra Cambria, Erik Teo, Leslie |
| contents | Recently, Large Language Models (LLMs) have dominated much of the artificial intelligence scene with their ability to process and generate natural languages. However, the majority of LLM research and development remains English-centric, leaving low-resource languages such as those in the Southeast Asian (SEA) region under-represented. To address this representation gap, we introduce Llama-SEA-LION-v3-8B-IT and Gemma-SEA-LION-v3-9B-IT, two cutting-edge multilingual LLMs designed for SEA languages. The SEA-LION family of LLMs supports 11 SEA languages, namely English, Chinese, Indonesian, Vietnamese, Malay, Thai, Burmese, Lao, Filipino, Tamil, and Khmer. Our work leverages large-scale multilingual continued pre-training with a comprehensive post-training regime involving multiple stages of instruction fine-tuning, alignment, and model merging. Evaluation results on multilingual benchmarks indicate that our models achieve state-of-the-art performance across LLMs supporting SEA languages. We open-source the models to benefit the wider SEA community. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_05747 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SEA-LION: Southeast Asian Languages in One Network Ng, Raymond Nguyen, Thanh Ngan Huang, Yuli Tai, Ngee Chia Leong, Wai Yi Leong, Wei Qi Yong, Xianbin Ngui, Jian Gang Susanto, Yosephine Cheng, Nicholas Rengarajan, Hamsawardhini Limkonchotiwat, Peerat Hulagadri, Adithya Venkatadri Teng, Kok Wai Tong, Yeo Yeow Siow, Bryan Teo, Wei Yi Lau, Wayne Tan, Choon Meng Ong, Brandon Ong, Zhi Hao Montalan, Jann Railey Chan, Adwin Antonyrex, Sajeban Lee, Ren Choa, Esther Tat-Wee, David Ong Liu, Bing Jie Darius Tjhi, William Chandra Cambria, Erik Teo, Leslie Computation and Language Recently, Large Language Models (LLMs) have dominated much of the artificial intelligence scene with their ability to process and generate natural languages. However, the majority of LLM research and development remains English-centric, leaving low-resource languages such as those in the Southeast Asian (SEA) region under-represented. To address this representation gap, we introduce Llama-SEA-LION-v3-8B-IT and Gemma-SEA-LION-v3-9B-IT, two cutting-edge multilingual LLMs designed for SEA languages. The SEA-LION family of LLMs supports 11 SEA languages, namely English, Chinese, Indonesian, Vietnamese, Malay, Thai, Burmese, Lao, Filipino, Tamil, and Khmer. Our work leverages large-scale multilingual continued pre-training with a comprehensive post-training regime involving multiple stages of instruction fine-tuning, alignment, and model merging. Evaluation results on multilingual benchmarks indicate that our models achieve state-of-the-art performance across LLMs supporting SEA languages. We open-source the models to benefit the wider SEA community. |
| title | SEA-LION: Southeast Asian Languages in One Network |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2504.05747 |