{"ID":2826303,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.19455","arxiv_id":"2512.19455","title":"SiamGPT: Quality-First Fine-Tuning for Stable Thai Text Generation","abstract":"Open-weights large language models remain difficult to deploy for Thai due to unstable generation under complex instructions, despite strong English performance. To mitigate these limitations, We present SiamGPT-32B, an open-weights model based on Qwen3-32B, fine-tuned with a Quality-First strategy emphasizing curated supervision over data scale. The fine-tuning pipeline combines high-complexity English instruction data with a Thai-adapted AutoIF framework for instruction and linguistic constraints. Using supervised fine-tuning only, without continual pretraining or corpus expansion, SiamGPT-32B improves instruction adherence, multi-turn robustness, and linguistic stability. Evaluations on the SEA-HELM benchmark show that SiamGPT-32B achieves the strongest overall performance among similar-scale open-weights Thai models, with consistent gains in instruction following, multi-turn dialogue, and natural language understanding.","short_abstract":"Open-weights large language models remain difficult to deploy for Thai due to unstable generation under complex instructions, despite strong English performance. To mitigate these limitations, We present SiamGPT-32B, an open-weights model based on Qwen3-32B, fine-tuned with a Quality-First strategy emphasizing curated...","url_abs":"https://arxiv.org/abs/2512.19455","url_pdf":"https://arxiv.org/pdf/2512.19455v3","authors":"[\"Thittipat Pairatsuppawat\",\"Abhibhu Tachaapornchai\",\"Paweekorn Kusolsomboon\",\"Chutikan Chaiwong\",\"Thodsaporn Chay-intr\",\"Kobkrit Viriyayudhakorn\",\"Nongnuch Ketui\",\"Aslan B. Wong\"]","published":"2025-12-22T15:00:25Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Language Model\"]","has_code":false}