Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

Language and Cognition01:27

Language and Cognition

303
Language serves as a bridge between ideas and communication, influencing how individuals perceive and interact with the world. Psychologists have long debated whether language shapes thought or vice versa. This discussion gained grip with Edward Sapir and Benjamin Lee Whorf in the 1940s, who proposed that language determines thought, a concept known as linguistic determinism. They suggested that the vocabulary and structure of a language influence how its speakers think and perceive reality.
303

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

Grounding large language models in clinical diagnostics.

Nature communications·2026
Same author

Remnant Preservation in Anterior Cruciate Ligament Reconstruction Versus Non-Preservation Methods: A Systematic Review and Meta-Analysis.

Orthopaedic surgery·2025
Same author

Evaluating and Enhancing Large Language Models' Performance in Domain-Specific Medicine: Development and Usability Study With DocOA.

Journal of medical Internet research·2024
Same author

Prompt engineering in consistency and reliability with the evidence-based guideline for LLMs.

NPJ digital medicine·2024
Same author

Self-supported catalysts.

Chemical reviews·2008
Same author

[The local control of radiotherapy following Ivor-Lewis esophagectomy in the patients with stage II A middle-third thoracic esophageal cancer].

Zhonghua wai ke za zhi [Chinese journal of surgery]·2008

相关实验视频

Updated: May 22, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

474

通过多代理对话式大型语言模型增强诊断能力.

Xi Chen1,2, Huahui Yi3,4,5, Mingke You1,2

  • 1Sports Medicine Center, Department of Orthopedics and Orthopedic Research Institute, West China Hospital, West China School of Medicine, Sichuan University, Chengdu, Sichuan, China.

NPJ digital medicine
|March 14, 2025
PubMed
概括
此摘要是机器生成的。

一个新的多代理对话 (MAC) 框架增强了医疗诊断的大型语言模型 (LLM). 这种由临床团队启发的AI方法,在复杂的罕见疾病病例中显著提高了诊断准确性.

更多相关视频

Examining Online Syntactic Processing of Spoken Complex Sentences in Chinese Using Dual-Modal Interference Tasks
08:32

Examining Online Syntactic Processing of Spoken Complex Sentences in Chinese Using Dual-Modal Interference Tasks

Published on: September 5, 2019

5.6K
Multimodal Protocol for Assessing Metacognition and Self-Regulation in Adults with Learning Difficulties
12:55

Multimodal Protocol for Assessing Metacognition and Self-Regulation in Adults with Learning Difficulties

Published on: September 27, 2020

8.3K

相关实验视频

Last Updated: May 22, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

474
Examining Online Syntactic Processing of Spoken Complex Sentences in Chinese Using Dual-Modal Interference Tasks
08:32

Examining Online Syntactic Processing of Spoken Complex Sentences in Chinese Using Dual-Modal Interference Tasks

Published on: September 5, 2019

5.6K
Multimodal Protocol for Assessing Metacognition and Self-Regulation in Adults with Learning Difficulties
12:55

Multimodal Protocol for Assessing Metacognition and Self-Regulation in Adults with Learning Difficulties

Published on: September 27, 2020

8.3K

科学领域:

  • 人工智能在医学中的应用
  • 临床决策支持系统 临床决策支持系统
  • 自然语言处理自然语言处理.

背景情况:

  • 大型语言模型 (LLM) 在医疗保健中显示出潜力,但在复杂的医学推理中扎.
  • 当前的LLM应用程序往往缺乏临床实践的协作和代性质.

研究的目的:

  • 开发和评估一个多代理对话 (MAC) 框架,以使用LLMs改进疾病诊断.
  • 将MAC框架的诊断性能与单个LLM模型和其他先进的AI方法进行比较.

主要方法:

  • 设计了一个MAC框架,模拟多学科团队与专门的AI代理商的讨论.
  • 该框架在302个罕见疾病病例中使用GPT-3.5和GPT-4作为基准模型进行了评估.
  • 性能与基线LLM,思维链 (CoT),自我精炼和自我一致性方法进行了比较.

主要成果:

  • 与单个LLM相比,MAC框架在初始和后续咨询中都显示出更高的诊断准确性和测试建议相关性.
  • 通过使用GPT-4的四个医生代理和一个监督代理的配置,可以实现最佳性能.
  • 在准确性和输出量方面,MAC始终优于其他比较方法,包括CoT,Self-Refine和Self-Consistency.

结论:

  • 多代理对话框架显著提高了LLM在医疗保健中的诊断能力.
  • 这种方法有效地弥合了理论医学知识和实际临床应用之间的差距.
  • 多代理的LLM系统在推进临床决策支持方面具有重大前景,并为实施提供了进一步的研究.