English(EN) Learning from Disagreement: Clinician Overrides as Implicit Preference Signals for Clinical AI in Value-Based Care

AI研究将临床医生否决重塑为价值医疗的隐式偏好信号

作者 PulseAugur 编辑部 · [2 个来源] · 2026-04-30 15:30

研究人员开发了一个新框架，将临床医生对AI建议的否决视为隐式偏好信号，类似于RLHF，但有专家标注者和可观察的结果。该方法引入了一个五类否决分类法和一个双学习架构来训练奖励模型和能力模型。该系统旨在防止“抑制偏差”，即由于临床医生的局限性而忽略了正确但困难的建议，尤其是在价值医疗环境中。 AI

影响这项研究可以通过更有效地利用专家反馈来改善临床AI系统的对齐和有效性。

排序理由这是一篇详细介绍临床AI新框架的研究论文。

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.AI TIER_1 English(EN) · Prabhjot Singh, Abhishek Gupta, Chris Betz, Abe Flansburg, Brett Ives, Sudeep Lama, Jung Hoon Son · 2026-05-01 04:00

Learning from Disagreement: Clinician Overrides as Implicit Preference Signals for Clinical AI in Value-Based Care

arXiv:2604.28010v1 Announce Type: cross Abstract: We reframe clinician overrides of clinical AI recommendations as implicit preference data - the same signal structure exploited by reinforcement learning from human feedback (RLHF), but richer: the annotator is a domain expert, th…
arXiv cs.AI TIER_1 English(EN) · Jung Hoon Son · 2026-04-30 15:30

Learning from Disagreement: Clinician Overrides as Implicit Preference Signals for Clinical AI in Value-Based Care

We reframe clinician overrides of clinical AI recommendations as implicit preference data - the same signal structure exploited by reinforcement learning from human feedback (RLHF), but richer: the annotator is a domain expert, the alternatives carry real consequences, and downst…