两篇研究论文介绍了优化大型语言模型（LLM）监督微调（SFT）的新颖方法。第一种方法“在线动态批处理”（ODB）通过将批处理形成移至准确可观察点来解决训练期间可变样本处理成本的挑战，将吞吐量提高了4.43倍。第二种方法“效用-多样性感知在线批处理选择”（UDS）侧重于在SFT期间选择有价值且多样化的数据样本，以防止过拟合和偏差放大，其性能优于现有方法并减少了训练时间。 AI
影响 这些方法旨在提高LLM微调的效率和有效性，可能导致更快的开发周期和更好的模型性能。
排序理由 两篇提出LLM训练优化新颖方法的学术论文。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2606.19989v1 Announce Type: cross Abstract: Modern LLM training breaks a core assumption behind offline batch samplers: the true training cost of a sample is only observable after preprocessing, augmentation, templating, tokenization, and multimodal visual-token expansion. …
Modern LLM training breaks a core assumption behind offline batch samplers: the true training cost of a sample is only observable after preprocessing, augmentation, templating, tokenization, and multimodal visual-token expansion. Unless one pays for a preprocessing- and augmentat…
arXiv:2510.16882v4 Announce Type: replace-cross Abstract: Supervised fine-tuning (SFT) is a commonly used technique to adapt large language models (LLMs) to downstream tasks. In practice, SFT on a full dataset is computationally expensive and sometimes suffers from overfitting or…