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

Non-equilibrium in the Cell01:16

Non-equilibrium in the Cell

4.0K
An important concept in studying metabolism and energy is that of chemical equilibrium. Most chemical reactions are reversible. They can proceed in both directions, releasing energy into their environment in one direction, and absorbing it from the environment in the other direction. The same is true for the chemical reactions involved in cell metabolism, such as the breaking down and building up of proteins into and from individual amino acids, respectively. Reactants within a closed system...
4.0K

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

Perinatal and Parental Predictors of Wheezing in the First Year of Life: A Saudi Arabian Birth Cohort Study.

Healthcare (Basel, Switzerland)·2026
Same author

Adapting Evidence-Based Practice Guidelines for Sedation, Analgesia, Withdrawal, and Delirium Assessment and Management in Critically Ill Children.

Critical care research and practice·2026
Same author

Validity and Reliability of the Arabic Voice Activity and Participation Profile (A-VAPP) Questionnaire.

Saudi medical journal·2026
Same author

Management of Dysphagia in Patients with Tracheostomy: Clinical Position Statement of the UEP Swallowing Committee.

Dysphagia·2026
Same author

Valganciclovir Dosing Strategies for Cytomegalovirus Prophylaxis in Pediatric Solid Organ Transplant Recipients: A Comparative Single-Center Study.

Viruses·2026
Same author

Travel-Related Challenges of Chikungunya Virus and Vaccination Options.

Journal of epidemiology and global health·2026

相关实验视频

Updated: May 6, 2026

Assessment and Communication for People with Disorders of Consciousness
07:37

Assessment and Communication for People with Disorders of Consciousness

Published on: August 1, 2017

9.0K

医学人工智能聊天机器人的参考幻觉评分:开发和可用性研究

Fadi Aljamaan1, Mohamad-Hani Temsah1, Ibraheem Altamimi1

  • 1College of Medicine, King Saud University, Riyadh, Saudi Arabia.

JMIR medical informatics
|July 31, 2024
PubMed
概括

一个新的参考幻觉评分 (RHS) 评估了AI聊天机器人在医学研究中的引用. 在Elicit和SciSpace中,幻觉的发生率很低,而在ChatGPT和Bing中,幻觉的发生率很高,这凸显了对验证工具的需求.

关键词:
这就是为什么BingBingBingBingBing.聊天GPT 聊天GPT 聊天引发 引发 引起困惑感 困惑感 困惑感科学空间空间科学空间人工智能 (AI) 聊天机器人聊天机器人文献鉴定验证 文献鉴定验证参考幻觉是一种参考幻觉.

更多相关视频

Evaluating Usability Aspects of a Mixed Reality Solution for Immersive Analytics in Industry 4.0 Scenarios
06:02

Evaluating Usability Aspects of a Mixed Reality Solution for Immersive Analytics in Industry 4.0 Scenarios

Published on: October 6, 2020

2.2K
The Immersive Cleveland Clinic Virtual Reality Shopping Platform for the Assessment of Instrumental Activities of Daily Living
08:36

The Immersive Cleveland Clinic Virtual Reality Shopping Platform for the Assessment of Instrumental Activities of Daily Living

Published on: July 28, 2022

3.7K

相关实验视频

Last Updated: May 6, 2026

Assessment and Communication for People with Disorders of Consciousness
07:37

Assessment and Communication for People with Disorders of Consciousness

Published on: August 1, 2017

9.0K
Evaluating Usability Aspects of a Mixed Reality Solution for Immersive Analytics in Industry 4.0 Scenarios
06:02

Evaluating Usability Aspects of a Mixed Reality Solution for Immersive Analytics in Industry 4.0 Scenarios

Published on: October 6, 2020

2.2K
The Immersive Cleveland Clinic Virtual Reality Shopping Platform for the Assessment of Instrumental Activities of Daily Living
08:36

The Immersive Cleveland Clinic Virtual Reality Shopping Platform for the Assessment of Instrumental Activities of Daily Living

Published on: July 28, 2022

3.7K

科学领域:

  • 医学研究 医学研究
  • 人工智能的人工智能是人工智能.
  • 科学写作 科学写作

背景情况:

  • 医疗保健从业者越来越多地使用AI聊天机器人.
  • 人工智能聊天机器人的输出,包括引用,可能包含幻觉.
  • 这些不准确性引发了人们对医疗环境中AI可靠性的担忧.

研究的目的:

  • 引入一种新的参考幻觉得分 (RHS) 来评估人工智能聊天机器人生成的引用的真实性.
  • 在不同的AI聊天机器人中量化和比较引用幻觉.

主要方法:

  • 六个人工智能聊天机器人被测试,每一个有10个医疗提示,每一个提示请求10个引用.
  • 在开发RHS时,考虑了文献详细信息和相关性,以提示关键词.
  • 对于个别引用,提示和提示类型 (基本与复杂) 计算了RHS.

主要成果:

  • 巴德没有产生引用. 在Elicit和SciSpace中,RHS是最低的 (1),而ChatGPT 3.5和Bing的RHS是最高的 (11).
  • 提示关键字的引用相关性是最常见的幻觉 (61.6%).
  • 对于复杂或基于场景的提示,AI聊天机器人产生了显著更高的幻觉得分.

结论:

  • 该研究强调了人工智能聊天机器人引用真实性的显著差异,需要强大的评估工具.
  • 在Elicit和SciSpace中,幻觉的程度很小,而在ChatGPT和Bing中,幻觉的程度很高.
  • 拟议的RHS可以帮助提高AI在医学研究中的可靠性和可信性.