paper-with-me

홈 › Papers

AtomiMed: Hierarchical Atomic Fact-Checking for Universal Clinical-Aware Medical Report Evaluation

2026-06-30 · Yuan Wang, Wanxing Chang, Songtao Jiang, Shujian Gao, Xiaotian Zhang, Ruifeng Yuan, Weiwei Cao, Bowen Shi, Ling Zhang, Zuozhu Liu, Jianpeng Zhang hf

Traditional metrics for Medical Report Generation (MRG) predominantly rely on surface-level n-gram overlap, which fails to capture clinical factual accuracy and often overlooks catastrophic diagnostic errors. We address this fundamental limitation by proposing AtomiMed, a universal, modality-agnostic evaluation framework that decomposes complex medical narratives into a standardized, multi-level hierarchy of Atomic Clinical Facts, encompassing Disease-level entities and Attribute-level descriptors, including location, morphology, and severity. By implementing an Agentic Cross-Verification loop between ground-truth and predicted reports, AtomiMed simulates a multi-radiologist peer-review process to verify clinical consistency, thus enabling the decoupled assessment of diagnostic detection and descriptive accuracy. To facilitate standardized evaluation, we introduce MRGEvalKit, an open-source toolkit for automated hierarchical extraction, and curate OmniMRG-Bench, a comprehensive multi-modal benchmark covering X-ray, CT, MRI, and Ultrasound. Extensive experiments on multiple expert-annotated reader studies demonstrate that AtomiMed achieves significantly higher correlation with human radiologist judgment compared to traditional and model-based metrics. Our code are release at https://github.com/Venn2336/MRGEvalkit

📄 PDF Abstract BibTeX arXiv:2606.31292

Code (0)

등록된 구현이 없습니다.

Tasks

Medical Report Generation

Similar Papers 제목 키워드 기반

Atomic Fact-Checking Increases Clinician Trust in Large Language Model Recommendations for Oncology Decision Support: A Randomized Controlled Trial

2026-05-05 · Lisa C. Adams, Linus Marx, Erik Thiele Orberg, Keno Bressem 외 arxiv

Question: Does atomic fact-checking, which decomposes AI treatment recommendations into individually verifiable claims linked to source guideline documents, increase clinician trust compared to traditional explainability…

FIRE: Fact-checking with Iterative Retrieval and Verification

2024-10-17 · Zhuohan Xie, Rui Xing, Yuxia Wang, Jiahui Geng 외

Fact-checking long-form text is challenging, and it is therefore common practice to break it down into multiple atomic claims. The typical approach to fact-checking these atomic claims involves retrieving a fixed number …

Claim VerificationFact CheckingLanguage ModelingLanguage Modelling+2

Evidence-based Interpretable Open-domain Fact-checking with Large Language Models

2023-12-10 · Xin Tan, Bowei Zou, Ai Ti Aw

Universal fact-checking systems for real-world claims face significant challenges in gathering valid and sufficient real-time evidence and making reasoned decisions. In this work, we introduce the Open-domain Explainable…

Fact Checkingvalid

Enhancing Health Fact-Checking with LLM-Generated Synthetic Data

2025-08-28 · Jingze Zhang, Jiahe Qian, Yiliang Zhou, Yifan Peng arxiv

Fact-checking for health-related content is challenging due to the limited availability of annotated training data. In this study, we propose a synthetic data generation pipeline that leverages large language models (LLM…

Synthetic Data GenerationData AugmentationFact Checking

Generating Label Cohesive and Well-Formed Adversarial Claims

2020-09-17 · EMNLP 2020 11 · Pepa Atanasova, Dustin Wright, Isabelle Augenstein

Adversarial attacks reveal important vulnerabilities and flaws of trained models. One potent type of attack are universal adversarial triggers, which are individual n-grams that, when appended to instances of a class und…

Fact CheckingLanguage ModelingLanguage ModellingNatural Language Inference+1