研究人员推出了 REMEDI，这是一个旨在评估专门用于多标签临床疾病推理的机器学习遗忘技术的新基准。由于患者数据的敏感性质和临床数据集的复杂性，现有的遗忘方法通常不适用于医疗应用。REMEDI 利用 MIMIC-III 数据库，并解决了标签相关性和安全约束等挑战，比合成数据集提供了更现实的评估。 AI
影响 提供了一种标准化的方法来测试 AI 模型在敏感医疗环境中的数据删除能力。
排序理由 该集群包含一篇介绍用于评估机器学习遗忘技术的新基准的研究论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.07141v1 Announce Type: cross Abstract: Language models trained for clinical disease inference are trained on patient data, which may include sensitive and private information, and data owners may request the removal of their data from a trained model due to privacy or …
Language models trained for clinical disease inference are trained on patient data, which may include sensitive and private information, and data owners may request the removal of their data from a trained model due to privacy or copyright concerns. However, exactly unlearning pa…