OmniMed-Jev 提出医疗多模态决策原生接口以校准置信度

1. 12:00
   arXiv · Machine Learning Theory

   OmniMed-Jev：通过决策原生接口校准大视觉语言模型置信度以实现可信医疗多模态决策

   OmniMed-Jev 将医疗决策表示为 Choice、None 或 Score 类型的概率分布，使报告置信度与真实准确率对齐。在与同骨干同数据同训练的生成式基线接口控制对比中，校准误差降低最多一个数量级，可靠性误差降低最多两倍，点预测性能相当；计数任务基线仍领先。代码已开源。

Current heat 9·Comparable peak 10（Oct 2）·Comparable change over 24 hours –

The trend compares only the same participants observed continuously; its range may be smaller than the current heat count. Move or click on the chart to inspect hourly heat; use the left and right arrow keys to switch.