研究人员开发了DecSelfMask，一种利用无标签数据提高仅解码器语言模型分类性能的新颖方法。该方法采用相关性引导掩码策略，识别关键文本片段并训练模型进行重构。在190万份临床笔记的数据集上，DecSelfMask在宏观F1分数上比标准的监督微调方法提高了近20个百分点，表现显著。 AI
影响 增强了仅解码器模型的分类能力，可能减少在专业领域对昂贵标签数据的依赖。
排序理由 该集群包含一篇详细介绍改进语言模型性能新方法的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.09466v2 Announce Type: replace Abstract: Classification tasks require annotated data, which can often be expensive, time-consuming, or even unfeasible to collect. This is the case of the medical domain, where large datasets often have few annotated examples. To address…
Classification tasks require annotated data, which can often be expensive, time-consuming, or even unfeasible to collect. This is the case of the medical domain, where large datasets often have few annotated examples. To address this, we propose DecSelfMask (Decoder Self-learning…