{"ID":2858649,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.08620","arxiv_id":"2510.08620","title":"JAI-1: A Thai-Centric Large Language Model","abstract":"This technical report introduces JAI-1, a Thai-centric language model with 75B parameters. Recent Thai models have primarily relied on existing open-source models, applying additional training without structural modifications to specialize in Thai. However, this approach risks eroding pre-existing knowledge in the model's parameter space during the injection of Thai-specific information, as optimized parameters for general tasks may conflict with new linguistic requirements. In contrast, JAI-1 adopts an upscaling strategy: starting from a smaller, high-performing English open-source LLM, we expanded its parameter space and utilized the newly allocated capacity to systematically integrate Thai-language knowledge. This methodology not only preserves the original model's general intelligence but also establishes a unique architecture distinct from other open-source models, enabling scalable future enhancements. During pre-training, JAI-1 was exposed to 1.5T tokens, including over 300B Thai language tokens. This was followed by post-training stages -- supervised fine-tuning and alignment tuning -- using more than 600K instruction-based examples. The final model demonstrated superior performance compared to Typhoon2-70B on Thai-centric benchmarks (IFEval-TH, MT-Bench-TH, and JAI-Hall-Bench), validating the efficacy of its upscaling and knowledge-integration framework.","short_abstract":"This technical report introduces JAI-1, a Thai-centric language model with 75B parameters. Recent Thai models have primarily relied on existing open-source models, applying additional training without structural modifications to specialize in Thai. However, this approach risks eroding pre-existing knowledge in the mode...","url_abs":"https://arxiv.org/abs/2510.08620","url_pdf":"https://arxiv.org/pdf/2510.08620v1","authors":"[\"Attapol T. Rutherford\",\"Jullajak Karnjanaekarin\",\"Narongkorn Panitsrisit\",\"Pontakorn Trakuekul\",\"Sumana Sumanakul\",\"Natchanon Pollertlam\"]","published":"2025-10-08T09:02:20Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}