一项发表在arXiv上的新研究探讨了大型语言模型（LLM）在预测1型糖尿病患者血糖事件方面的有效性。该研究使用了OhioT1DM数据集，发现生理信息在提示中的表述方式显著影响LLM的性能。虽然传统的监督模型在预测高血糖方面表现出色，但基于提示的LLM在预测低血糖方面有所改进，其性能随提供的信息和预测范围的变化而变化。 AI
影响 强调了提示工程对于LLM在专业医疗预测任务中的重要性。
排序理由 该集群包含一篇详细介绍LLM应用新研究发现的学术论文。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2609.08772v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly being investigated for physiological time-series prediction, yet their effectiveness may depend not only on the model itself, but also on how physiological information is represented and…
Large Language Models (LLMs) are increasingly being investigated for physiological time-series prediction, yet their effectiveness may depend not only on the model itself, but also on how physiological information is represented and presented at inference time. This study investi…