arXiv cs.AI· Sara Khosravi, Xiaofei Wen, Majid Sarrafzadeh, Muhao Chen·· 4 小时前AI 评分34
MedGuardBench:面向个性化护栏开发的以患者为中心基准
MedGuardBench: A Patient-Oriented Benchmark for Personalized Guardrail Development
AI 导读
研究团队发布 MedGuardBench,一个覆盖 87 种药物、5,001 个场景的药物不相交基准,用于评估患者条件化的用药安全护栏。研究发现标准护栏依赖措辞和是否提供档案等表面线索,而非患者事实。为此提出的个性化推理护栏包含个性化推理蒸馏、Context Unrolling 和基于规则的奖励(guided GRPO),在准确率上优于基座模型,并相对无档案对照组减少误报。
正文 · 原文
Abstract:Safety is personal: the same action can be safe for one person but unsafe for another. Yet current guardrails judge content without considering who is affected. Using medication safety, we introduce \textit{patient-conditioned medication guarding}, which predicts a safety verdict and 17 risk categories from a patient profile and prescription. We release \textbf{MedGuardBench}, a drug-disjoint benchmark of 5{,}001 scenarios across 87 medications. We find that standard guardrails rely on surface cues, such as wording and profile presence, rather than patient facts. To address this, we develop \textit{personalized reasoning guardrails} with three components. \textbf{Personalized Reasoning Distillation} links risks to relevant patient fields. \textbf{Context Unrolling (CU)} makes models check each field themselves, reducing false alarms on most backbones; controls show that providing the check does not yield the same benefit. A \textbf{rule-based reward (guided GRPO)} improves unsafe recall and complex-risk detection, including allergies and adverse reactions, on some backbones, but increases false alarms on others. Our models outperform base models and matched no-profile controls in accuracy, while reducing false alarms relative to no-profile controls. Profile removal and swapping confirm that gains come from patient information, not fine-tuning alone.
| Subjects: | Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2611.22069 [cs.AI] |
| (or arXiv:2611.22069v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.22069 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Sara Khosravi [view email]
[v1]
Tue, 17 Nov 2026 01:46:53 UTC (5,069 KB)
来源:arXiv cs.AI · arxiv.org