发表机构
Carnegie Mellon University; University of Wisconsin–Madison; Mohamed bin Zayed University of AI; GenBio AI; Intel（卡内基梅隆大学; 威斯康星大学麦迪逊分校; 穆罕默德·本·扎耶德人工智能大学; 基因生物人工智能公司; 英特尔公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对医疗保健领域特定任务零样本模型问题推出检索增强可解释学习（RAIL）框架，通过检索相关任务并传递结构生成新预测器，概率公式提供不确定性支持可靠性感知部署，在临床程序预测任务中性能可靠，还提升模型透明度。
AI 中文摘要
我们引入了检索增强可解释学习（RAIL），这是一个概率元学习框架，用于零样本生成特定任务的可解释模型，该模型从自然语言任务描述和先前学习的特定任务预测器的记忆中合成系数空间结构。RAIL检索相关源任务，通过系数空间传递结构，并在原始诊断特征空间中生成新的预测器，实现具有特征级解释的零样本和少样本临床程序预测。其概率公式提供了检索、模型系数和预测的不确定性，支持可靠性感知部署。在长尾临床程序预测任务中，RAIL在不同数据可用性情况下保持可靠性能，在零样本设置中准确率达73.4%，在极少样本情况下准确率接近73.2%。RAIL还受益于临床信息任务表示，并产生检索、不确定性和系数级诊断，使模型行为更透明。这些结果为可扩展临床预测系统指明了道路，该系统可适应新任务，同时保持可解释性和可靠性。
英文摘要
We introduce Retrieval-Augmented Interpretable Learning (RAIL), a probabilistic meta-learning framework for zero-shot generation of task-specific interpretable models that synthesizes coefficient-space structure from natural-language task descriptions and a memory of previously learned task-specific predictors. RAIL retrieves related source tasks, transfers structure through coefficient space, and generates a new predictor in the original diagnostic-feature space, enabling zero-shot and few-shot clinical procedure prediction with feature-level explanations. Its probabilistic formulation provides uncertainty over retrieval, model coefficients, and predictions, supporting uncertainty-aware deployment: uncertain predictions or unstable explanations can be flagged for additional clinical review rather than treated as automatic decisions. This makes RAIL particularly suited for healthcare settings, where prediction tasks are highly long-tailed, new clinical targets arise frequently, and models must remain inspectable, uncertainty-aware, and compatible with human oversight. Across long-tailed clinical procedure prediction tasks, RAIL improves low-data model generation, benefits from clinically informed task representations, and yields retrieval, uncertainty, and coefficient-level diagnostics that make model behavior more transparent. These results suggest a path toward scalable clinical prediction systems that can adapt to new tasks while preserving interpretability and reliability.
CommentsWe note that a preliminary, non-archival workshop version of this work is available online under the name RAG-IM. RAIL is the renamed and completed version of the same work. This manuscript supersedes that earlier non-archival workshop version and should be consulted for the current formulation, results, and contributions
