CARE：面向医学摘要的保形安全层
CARE: A Conformal Safety Layer for Medical Summarization
AI总结：
提出CARE方法，通过保形风险控制为LLM医学摘要提供校准的遗漏和幻觉标记，在保证安全性的同时减少审查负担。
摘要：
大型语言模型（LLM）越来越多地用于医学摘要，但其输出可能遗漏重要的医学信息并引入无根据的陈述。现有的错误检测方法产生启发式或未校准的分数，无法对遗漏错误进行正式控制，也无法以原则性的方式在安全性与临床医生审查负担之间进行权衡。我们引入了风险评估的保形评估（CARE），这是一种事后、模型无关的安全层，使用保形风险控制为任何LLM生成的摘要叠加校准的遗漏和幻觉标记，无需重新训练。CARE通过两个控制器提供有限样本、分布无关的保证：一个幻觉控制器，限制包含任何未标记幻觉句子的文档的概率；一个遗漏控制器，限制未提交审查的重要遗漏的期望比例。与幻觉检测不同，遗漏同时取决于源句子是否重要以及摘要是否覆盖该句子。我们表明，仅校准一个维度可能违反目标风险界限，而边际分解虽然有效但过于保守。通过在整个$(τ,γ)$阈值空间上进行联合校准，CARE在保持正式保证的同时，比替代的校准基线最多减少5倍的标记句子。在五个医学摘要任务中，CARE在100次校准/测试重划分中，以95%的置信度满足$α=0.15$的目标风险界限，每个领域仅使用约100个标记文档。在一项初步的临床医生研究（75份文档审查）中，校准标记平均将遗漏检测提高了28.6个百分点。这些结果表明，句子级别的安全保证对于LLM辅助的医学摘要是可行的，并为平衡残余风险和审查工作量提供了一种可调节的机制。
英文摘要：
Large language models (LLMs) are increasingly used for medical summarization, but their outputs can omit medically important information and introduce unsupported claims. Existing error-detection methods produce heuristic or uncalibrated scores, providing no formal control over missed errors and no principled way to trade off safety against clinician review burden. We introduce Conformal Assessment for Risk Evaluation (CARE), a post-hoc, model-agnostic safety layer that uses conformal risk control to overlay calibrated omission and hallucination flags onto summaries from any LLM without retraining. CARE provides finite-sample, distribution-free guarantees through two controllers: a hallucination controller that bounds the probability of a document containing any unflagged hallucinated sentence, and an omission controller that bounds the expected fraction of important omissions not surfaced for review. Unlike hallucination detection, omissions depend jointly on whether a source sentence is important and whether it is covered by the summary. We show that calibrating only one dimension can violate the target risk bound, while marginal decompositions remain valid but overly conservative. By jointly calibrating over the full $(τ,γ)$ threshold space, CARE preserves formal guarantees while surfacing up to 5$\times$ fewer sentences than alternative calibrated baselines. Across five medical summarization tasks, CARE satisfies the target risk bound at $α= 0.15$ with 95% confidence across 100 calibration/test resplits, using only ~100 labeled documents per domain. In a preliminary clinician study (75 document reviews), calibrated flags improved omission detection by 28.6 percentage points on average. These results show that sentence-level safety guarantees are feasible for LLM-assisted medical summarization and offer a tunable mechanism for balancing residual risk and review effort.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
