mlsanityData to 7 Oct 2026

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

arXiv 2605.21949 ↗First posted 21 May 2026cs.CLcited by 0

On the map: Retrieval-augmented generation → Medical and biomedical RAG

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Medical and biomedical RAG, one of 15 directions in Retrieval-augmented generation. Builds on 30 of its 33 references that are in the map. First posted on arXiv 21 May 2026.

Builds on

30 of 33 references.

References · 30

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  3. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  4. 2022Large Language Models Encode Clinical Knowledgecited by 1,807
  5. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  6. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,366
  7. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,362
  8. 2020What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Examscited by 1,324
  9. 2019PubMedQA: A Dataset for Biomedical Research Question Answeringcited by 1,271
  10. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,259
  11. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
  12. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,054
18 more
  1. 2020Beyond Accuracy: Behavioral Testing of NLP models with CheckListcited by 979
  2. 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 895
  3. 2019Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inferencecited by 864
  4. 2017Selective Classification for Deep Neural Networkscited by 799
  5. 2023Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generationcited by 795
  6. 2018Annotation Artifacts in Natural Language Inference Datacited by 656
  7. 2023Enabling Large Language Models to Generate Text with Citationscited by 584
  8. 2022MedMCQA : A Large-scale Multi-Subject Multi-Choice Dataset for Medical domain Question Answeringcited by 525
  9. 2020Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamicscited by 423
  10. 2021Measuring Attribution in Natural Language Generation Modelscited by 253
  11. 2024MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documentscited by 251
  12. 2020Selective Question Answering under Domain Shiftcited by 228
  13. 2021Get Your Vitamin C! Robust Fact Verification with Contrastive Evidencecited by 222
  14. 2023Query Rewriting for Retrieval-Augmented Large Language Modelscited by 211
  15. 2021A Dataset for Answering Time-Sensitive Questionscited by 150
  16. 2024Long-form factuality in large language modelscited by 146
  17. 2022FaithDial: A Faithful Benchmark for Information-Seeking Dialoguecited by 108
  18. 2020Knowing What You Know: Calibrating Dialogue Belief State Distributions via Ensemblescited by 8

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025MedTrust-RAG: Evidence Verification and Trust Alignment for Biomedical Question Answering
  2. 2026MedRAGChecker: Claim-Level Verification for Biomedical Retrieval-Augmented Generation
  3. 2026SURE-RAG: Sufficiency and Uncertainty-Aware Evidence Verification for Selective Retrieval-Augmented Generation
  4. 2026RAG-X: Systematic Diagnosis of Retrieval-Augmented Generation for Medical Question Answering
  5. 2026When Retrieval Helps and Distracts: Evaluating Evidence-Generating LLMs for Biomedical Claim Verification
  6. 2026Towards Query-Agnostic RAG Evaluation via Query Coverage and Claim Verifiability
  7. 2025MedCoT-RAG: Causal Chain-of-Thought RAG for Medical Question Answering
  8. 2026ClinicalBench: Stress-Testing Assertion-Aware Retrieval for Cross-Admission Clinical QA on MIMIC-IV