研究人员开发了一个新颖的零样本主动特征获取（AFA）框架，通过规范的诱导过程利用大型语言模型（LLMs）。该方法侧重于从LLMs中提取特定的统计信息，如一元偏差和成对协方差，然后用于指导分类或排序任务的特征选择。该框架在炎症性肠病（IBD）患者队列上进行了评估，在复杂病例方面表现优于现有方法。 AI
影响 这项研究通过在复杂患者病例中实现更有效的特征选择，有可能提高医疗保健的诊断准确性和效率。
排序理由 该集群包含两篇相同的arXiv预印本，详细介绍了一种新的研究方法。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2606.18933v1 Announce Type: new Abstract: Active feature acquisition (AFA) sequentially selects which features to observe to reach a classification or ranking decision. Its central limitation is reliance on large amount of labeled data to fit probabilistic models guiding ac…
Active feature acquisition (AFA) sequentially selects which features to observe to reach a classification or ranking decision. Its central limitation is reliance on large amount of labeled data to fit probabilistic models guiding acquisition. Large language models (LLMs) supply u…
Active feature acquisition (AFA) sequentially selects which features to observe to reach a classification or ranking decision. Its central limitation is reliance on large amount of labeled data to fit probabilistic models guiding acquisition. Large language models (LLMs) supply u…