OpenMTB‑Audit is an open‑source benchmark that tests large language models on 500 synthetic non‑small cell lung cancer cases, covering five adversarial error categories and four safety labels: Supported, Partially Supported, Unsupported, and Insufficient Information. The study found that all eight tested LLMs over‑refused Partially Supported recommendations, collapsing labels to achieve high safety scores. A deterministic seven‑module framework, MTB‑AuditAgent, was introduced to reduce over‑refusal to 6.7% and reach 91.2% accuracy, while an oncologist annotation study highlighted disagreement around the boundary between information sufficiency and treatment optimization.
By Negin Ashrafi, Jia Luo, Stacey M. Frumm, Roxana Daneshjou
arXiv:2607. 04907v1 Announce Type: new Abstract: Deploying Large Language Models (LLMs) in high-stakes clinical settings remains limited by structural hallucinations, weak deterministic reasoning over tabular patient data, and omissions in vector retrieval.
By Mohammed Saim Ahmed Quadri, Yunzhe Xue, Justin W. Ady, Usman Roshan
arXiv:2608.28974v1 Announce Type: new
Abstract: Clinically relevant oncology information is distributed across heterogeneous, longitudinal documentation, creating substantial abstraction burden and r...
By Daniel Kang, Michelle Hu, Soorya Ram Shimgekar, Shayan Vassef, Yufan Wang, Anit Kumar Sahu, Munmun De Choudhury, Vedant Das Swain, Christian Poellabauer, Li Yan Khor, Koustuv Saha, Robert Wojciechowski, Elliot Kidd, Piyum Zonooz, Navin Kumar
arXiv:2610.08660v1 Announce Type: new
Abstract: Background: Biomedical AI can generate plausible explanations without reliably verifying whether each statement is supported by patient-specific eviden...
By Mariya Miteva, Maria Nisheva-Pavlova
arXiv:2608.30912v1 Announce Type: new
Abstract: Artificial intelligence (AI) and natural language processing (NLP) are increasingly used to extract, integrate, and interpret biomedical knowledge rele...
By Bahar \.Ilgen, Yiannos Tolias, Denise K\"uhnert, Paraskevi Papadopoulou, Magnus Westerlund, Dominik Heider, Katharina Ladewig, Georges Hattab
Artificial intelligence (AI) and natural language processing (NLP) are increasingly used to extract, integrate, and interpret biomedical knowledge relevant to cancer genomics, yet their translation in...
The paper investigates why retrieval‑based open‑ended evaluation fails in medical fact verification. By creating two detailed taxonomies—one for retrieval‑stage errors across five quality dimensions and another for verifier‑reasoning errors across six steps—the authors automatically label evidence quality and reasoning errors using an LLM‑as‑Judge pipeline. Their large‑scale stress tests across multiple retrieval methods and verifier models show that increasing model size, reasoning effort, source breadth, or medical fine‑tuning does not eliminate these failure modes, indicating fundamental limits of the retrieve‑then‑verify paradigm in open‑ended medical contexts.
By Heyuan Huang, Jirui Dai, Alexandra DeLucia, Sonal Joshi, Mahsa Yarmohammadi, Jie Gao, Bernal Jim\'enez Guti\'errez, Mark Dredze
arXiv:2608. 02615v1 Announce Type: cross Abstract: Cancer diagnosis and characterization require integrating complementary evidence from radiology, pathology, genomics, and clinical metadata.
By Ahnaf Munir, Dannong Wang, Michael W. McDonald, Mubarak Shah, Pegah Khosravi, Yu Tian
arXiv:2607. 24371v1 Announce Type: cross Abstract: Healthcare interoperability requires AI systems to produce structured outputs conforming to standardized schemas including ICD-10 for diagnostic coding, CPT for procedure billing, and HL7 FHIR for data exchange.
By Jianru Shen
arXiv:2608.28592v1 Announce Type: new
Abstract: Large language models (LLMs) achieve high scores on medical knowledge examinations, yet real-world oncology is not a knowledge test--it is a sequence o...
By Zhang Sheng, Jinming Li, Wangyang Chen, Zhiwei Bao, Yu YoSean Wang
arXiv:2606. 09500v1 Announce Type: new Abstract: Objective.
By Yoojin Nam, Jinhoon Jeong, Namkug Kim
The article presents a new semantic model for representing scientific evidence, specifically tailored to genetics, that extends existing standards by adding fine‑grained, domain‑specific structure. It aligns with FHIR Evidence and SEPIO, incorporates a compact vocabulary validated by SHACL, and was tested in a human‑AI annotation pilot on six genetics papers, producing 28 evidence items and 95 source‑anchored assertions. The authors argue that this model advances trustworthy, AI‑ready infrastructure for variant interpretation by providing a reference data model and validation schema for genetic evidence.
By Michael Bouzinier, Dmitry Etin