# Claim-Selective Certification for High-Risk Medical Retrieval-Augmented Generation

Source: [Claim-Selective Certification for High-Risk Medical Retrieval-Augmented Generation](<https://www.sota2.com/research/paper/6a0fe325f984739ed6739e69>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-05-23T05:00:04.712Z

Authors: Shao Kan

Published: 2026-05-21T03:29:50.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Medical Question Answering on Medical QA Primary Split n = 314 (dev)](<https://www.sota2.com/research/sota/medical-question-answering-on-medical-qa-primary-split-n-314-dev.md>): Medical Question Answering; Medical QA Primary Split n = 314 (dev); UCCR: 0.

- [Medical Question Answering on Medical QA Primary n=319 (test)](<https://www.sota2.com/research/sota/medical-question-answering-on-medical-qa-primary-n-319-test.md>): Medical Question Answering; Medical QA Primary n=319 (test); UCCR: 0.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2605.21949>)

[PDF](<https://arxiv.org/pdf/2605.21949.pdf>)