Claim-Selective Certification for High-Risk Medical Retrieval-Augmented Generation
Medical RAG systems in high-risk QA settings are often evaluated through a single answer-or-abstain decision, but mixed evidence may support one claim, require conditions for another, and contradict a third. We study claim-selective certification: each response is decomposed into verifiable claims, scored against retrieved evidence, and mapped by an intent-aware selector to {full, partial, conflict, abstain}. On the primary weak-label certificate protocol, whose real-source-only dev/test rows cover the naturally occurring non-abstain actions, the full system records UCCR=0.0000, PAU=1.0000, PAU Precision=0.9901, and action accuracy=0.9204 on dev (n=314), and UCCR=0.0000, PAU=0.9967, PAU Precision=0.9739, and action accuracy=0.8997 on test (n=319). UCCR measures unsupported-claim risk within the certificate definition, and a source-missing counterfactual slice evaluates abstain under empty evidence. Shortcut controls quantify the action-label prior explained by source and intent metadata, while source/evidence-novel slices characterize transfer boundaries. The resulting interface separates action-label prediction from evidence-linked claim selection under mixed evidence.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
A Farewell to Harms: Risk Management for Medical Devices via the Riskman Ontology & Shapes
We introduce the Riskman ontology & shapes for representing and analysing information about risk management for medical devices. Risk management is concerned with taking necessary precautions so a medical device does not…
ManagementWhen Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation
LLMs are widely used, yet they remain prone to factual errors that erode user trust and limit adoption in high-risk settings. One approach to mitigate this risk is to equip models with uncertainty estimation mechanisms t…
Text GenerationSelective Risk Certification for LLM Outputs via Information-Lift Statistics: PAC-Bayes, Robustness, and Skeleton Design
Large language models often produce confident but incorrect outputs, creating a critical need for reliable uncertainty quantification with formal abstention guarantees. We introduce information-lift certificates that com…
Position: Certified Robustness Does Not (Yet) Imply Model Security
While certified robustness is widely promoted as a solution to adversarial examples in Artificial Intelligence systems, significant challenges remain before these techniques can be meaningfully deployed in real-world app…
PositionOnRAMP for Regulating AI in Medical Products
Medical Artificial Intelligence (AI) involves the application of machine learning algorithms to biomedical datasets in order to improve medical practices. Products incorporating medical AI require certification before de…
BIG-bench Machine Learning