针对泰语生成不稳问题，用精选数据微调大模型提升准确性。
SiamGPT: Quality-First Fine-Tuning for Stable Thai Text Generation
- 基于Qwen3-32B，采用精选监督数据微调策略
- 在SEA-HELM上表现优于同规模开源泰语模型
- 适合需要稳定泰语生成的场景，如客服、对话系统
开放权重的大语言模型在泰语场景下仍面临复杂指令下的生成不稳定性问题，尽管其英文表现优异。为此，我们提出SiamGPT-32B，基于Qwen3-32B，通过强调高质量监督而非数据规模的「质量优先」策略进行微调。该方法结合高复杂度英文指令数据与适配泰语的AutoIF框架，用于指令与语言约束建模。仅使用监督微调，未引入持续预训练或语料扩展，SiamGPT-32B显著提升了指令遵循能力、多轮对话鲁棒性及语言稳定性。在SEA-HELM基准测试中，SiamGPT-32B在同类规模开源泰语模型中取得最优综合性能，各项指标均实现一致提升。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。