Новости
Evaluating Multi-Turn Multimodal Diagnostic Reasoning on Challenging Real-World Clinical Cases
arXiv cs.AI · Опубликовано · 3 мин чтения
За 30 секунд
- Что произошло
- Researchers released ClinMM-Bench, a benchmark with 1,089 real-world clinical cases and 3,760 medical images to evaluate how well AI models perform multi-turn diagnostic reasoning across eight medical specialties.
- Почему это важно
- Engineers building or evaluating medical AI systems need this to understand current model limitations in clinical diagnostic tasks and reasoning quality beyond single-turn interactions.
- На что обратить внимание
- Even top proprietary models showed limited completely correct diagnoses. Models struggle with information synthesis, knowledge mapping, perception errors, premature closure, and visual hallucination in real clinical scenarios.
Послушать это резюме
Из статьи
-->
Computer Science > Computation and Language
arXiv:2607.25933v1 (cs)
[Submitted on 28 Jul 2026]
Title: Evaluating Multi-Turn Multimodal Diagnostic Reasoning on Challenging Real-World Clinical Cases
Authors: Rui Yang , Weihao Xuan , Yi Lin , Zhuhan Bao , Jonathan Chong Kai Liew , Matthew Yu Heng Wong , Nicolás Lescano , Nikita R. Paripati , Emily Ling-Lin Pai , Jiarui Liu , Heli Qi , Heng-Jui Chang , Benny Kai Guo Loo , Huitao Li , Kunyu Yu , Yufan Wang , Chuan Hong , Shijian Lu , Douglas Teodoro , Naoto Yokoya , Ross Koppel , Mona Diab , Hua Xu , David W. Bates , Nan Liu , Yifan Peng
View a PDF of the paper titled Evaluating Multi-Turn Multimodal Diagnostic Reasoning on Challenging Real-World Clinical Cases, by Rui Yang and 25 other authors
View PDF HTML (experimental)
Abstract: Clinical diagnostic evaluation should not only assess whether models can provide correct diagnoses, but also reflect the realities of clinical practice, including progressive disclosure of multimodal information, dynamic updating of diagnostic hypotheses, and continuous refinement of clinical reasoning. However, existing evaluations of multimodal large language models (MLLMs) typically rely on single-turn or isolated tasks, making it difficult to fully capture the complexity of real-world clinical diagnosis. To bridge this gap, we developed ClinMM-Bench, the largest multi-turn multimodal clin
Фрагмент оригинала. Полный текст читайте в первоисточнике.
- llm
- language model
- reasoning
The Agent Architect
Один паттерн, один компромисс, одна история сбоя в продакшене. Короткий еженедельный брифинг для тех, кто строит агентные системы.
Одно письмо в неделю, отписка в один клик. Адрес используется только для рассылки брифинга.