arXiv AI
Oct 2

A rubric landscape for evaluating clinical reasoning in large language models: what exists, what is missing, and what needs to be combined

The article reviews existing tools for assessing clinical reasoning in large language models, identifying six key dimensions—problem representation, temporal synthesis, differential and management reasoning, counterfactual reasoning, calibrated uncertainty, and reasoning faithfulness. It finds that no single instrument covers all dimensions, with some aspects reasonably addressed while others, especially faithfulness and counterfactual reasoning, remain weakly evaluated. The authors propose combining current tools through binary rubric items, separate completeness and correctness scores, importance weighting, safety caps, temporal consistency checks, and chance‑corrected reliability reporting, and call for further design work on uncertainty, counterfactual reasoning, and faithfulness in longitudinal free‑text contexts.

By Zhangshu Joshua Jiang, Zina Ibrahim, James T. Teo
arXiv Computation and Language
6d ago

An evidence-traceable benchmark of clinical reasoning in large language models

The paper introduces Med Evidence Bench (MEB), a benchmark of 1,536 physician‑constructed items covering guideline knowledge, standardized clinical scenarios, and real‑world laboratory scenarios, each linked to a versioned source‑text span. Across ten large language models, the Evidence Trace Score (ETS) ranged from 0.975 to 0.997 for guideline knowledge, 0.292 to 0.658 for standardized scenarios, and 0.182 to 0.447 for real‑world scenarios, with varying rankings across levels. Automated grading on 1,296 criterion‑level judgments matched the majority vote of three physicians with a macro‑F1 of 0.930, though agreement was lower for evidence application.

By Zhiqun Zhao (Advanced Medical Research Institute and Key Laboratory for Experimental Teratology of the Ministry of Education, Cheeloo College of Medicine, Shandong University, Jinan, China), Xiaodong Yang (Department of Urology, Shandong Provincial Hospital Affiliated to Shandong First Medical University, Jinan, China), Bruce Gu (Shandong Computer Science Center, National Supercomputer Center in Jinan, Jinan, China, Qilu University of Technology, Shandong Academy of Sciences, Jinan, China), Ming Li (Department of Rheumatology and Immunology, Shandong Provincial Hospital Affiliated to Shandong First Medical University, Jinan, China), Yi Fu (Information Network Management Office, Shandong Provincial Hospital Affiliated to Shandong First Medical University, Jinan, China), Song Li (Department of Medical Oncology, Qilu Hospital, Shandong University, Jinan, China), Qi Mei (Department of Oncology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China), Zhi Liu (Department of Clinical Laboratory, Shandong Provincial Hospital Affiliated to Shandong First Medical University, Jinan, China), Kai Zhang (Department of Breast Surgery, General Surgery, Qilu Hospital, Shandong University, Jinan, China), Kexue Fu (Shandong Computer Science Center, National Supercomputer Center in Jinan, Jinan, China, Qilu University of Technology, Shandong Academy of Sciences, Jinan, China), Jing Wu (Department of Central Laboratory, Public Health Clinical Center Affiliated to Shandong University, Shandong University, Jinan, China), Xiaofei Lu (Department of Breast Surgery, The First Affiliated Hospital of Shandong First Medical University, Jinan, China), Yule Li (Advanced Medical Research Institute and Key Laboratory for Experimental Teratology of the Ministry of Education, Cheeloo College of Medicine, Shandong University, Jinan, China), Zheng Wang (Department of Urology, Shandong Provincial Hospital Affiliated to Shandong First Medical University, Jinan, China), Haiquan Lu (Advanced Medical Research Institute and Key Laboratory for Experimental Teratology of the Ministry of Education, Cheeloo College of Medicine, Shandong University, Jinan, China), Xiaoming Wu (Shandong Computer Science Center, National Supercomputer Center in Jinan, Jinan, China, Qilu University of Technology, Shandong Academy of Sciences, Jinan, China)
Hugging Face Trending Papers
Nov 10

An evidence-traceable benchmark of clinical reasoning in large language models

The paper introduces Med Evidence Bench (MEB), a benchmark of 1,536 physician-constructed items that assess clinical reasoning in large language models (LLMs) across guideline knowledge, standardized scenarios, and real‑world laboratory scenarios. Each medical claim in the benchmark is linked to a versioned source‑text span, enabling evidence traceability. Across ten LLMs, the Evidence Trace Score (ETS) varied widely by level, with high guideline recall but lower performance on real‑world scenarios and evidence application.

arXiv Computation and Language
Aug 27

Retrieval-Augmented Agentic Rubric Generation for Reliable Medical Response Evaluation

The paper introduces a retrieval‑augmented multi‑agent framework that automatically generates instance‑specific evaluation rubrics for medical language models. By retrieving authoritative medical evidence, decomposing it into atomic facts, and combining these with user interaction constraints, the system produces fine‑grained criteria that outperform GPT‑4o on HealthBench and LLMEval‑Med. The generated rubrics also guide response refinement, improving medical LLM output quality by 9.2%.

By Yinzhu Chen, Abdine Maiga, Hossein A. Rahmani, Emine Yilmaz
arXiv AI
Oct 16

AI Consilium: a Benchmark of LLM Clinical Multidisciplinary Second Opinions

The paper introduces AI Consilium, a benchmark for evaluating large language models (LLMs) on providing clinically grounded, coherent, actionable, and safe second opinions in multidisciplinary settings. Using 300 NEJM–MedQA cases, the study compares eight single-model pipelines that generate role-specific opinions and interactive-consilium reports under free-form and structured conditions. Results show that structured final reports generally score higher, especially in management, and that GPT‑5.6‑Sol outperforms other models across all evaluated components, demonstrating the benchmark’s ability to differentiate model capabilities and the impact of response structure.

By Alexey A. Bokov, Ivan I. Panin, Nikolay B. Nechaev, Mikhail Yu. Valkov, Valeria Yu. Chernina, Natalia Gombolevskaya, Ayyaz Hussain, Vladimir M. Agafonov, Victor A. Gombolevskiy, Aleksandr V. Nesterov, Iaroslav R. Bespalov, Ivan V. Oseledets, Dmitry V. Dylov