相关实验视频

Updated: Jun 3, 2025

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

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

Published on: December 6, 2024

转变文学选:大型语言模型在系统审查中的新兴作用

Fernando M Delgado-Chaves¹, Matthew J Jennings², Antonio Atalaia³

¹Institute for Computational Systems Biology, Faculty of Mathematics, Informatics and Natural Sciences, University of Hamburg, Hamburg 22761, Germany.

Proceedings of the National Academy of Sciences of the United States of America

|January 6, 2025

概括

大型语言模型 (LLM) 可以通过自动化文献选来显著帮助系统审查. 这些人工智能工具显示出降低审核员工作负担高达93%的潜力,尽管仔细的标准定义是关键.

科学领域:

医疗信息学医疗信息学
医疗保健中的人工智能
证据综合证据综合

背景情况:

系统性审查 (SR) 对基于证据的医学至关重要,但需要广泛的手动查.
大型语言模型 (LLM) 为文学选择提供了潜在的自动化,但它们的性能需要评估.
在SR查中评估LLM与人类审查员的有效性对于在研究中采用AI至关重要.

研究的目的:

评估18个不同的LLM在标题和摘要选中的表现,以进行系统审查.
为了在三个系统性审查中比较LLM和人类审稿人之间的文献选择重叠.
为了确定影响LLM绩效的因素,在对文章进行系统审查时进行分类.

主要方法:

在三个系统性审查中,18名LLM和人类审稿人之间的文章选择的比较.
标题和摘要选准确性的分析,用于LLMs的包含/排除文章.
调查纳入标准定义和研究设计对LLM绩效的影响.

主要成果:

LLM与人类选择的文章有不同程度的重叠,分类样本大小因技术差异而不同.
平均而言,LLM正确地分类了三个SR中的大量标题和摘要.
法学士课程的成绩受到准确的纳入/排除标准和研究设计的精确措辞的影响.

结论:

在系统审查标题和摘要选中,LLM可以大幅减少单个审稿人的工作负担,从33%到93%不等.
优化纳入和排除标准的制定对于最大限度地发挥LLM在系统审查中的支持作用至关重要.
在证据综合中进一步完善LLM应用是有必要的,专注于标准清晰度和模型适应性.

关键词:

大型语言模型.文学选文学选系统性审查是系统的审查.

更多相关视频

Lexical Decision Task for Studying Written Word Recognition in Adults with and without Dementia or Mild Cognitive Impairment

Lexical Decision Task for Studying Written Word Recognition in Adults with and without Dementia or Mild Cognitive Impairment

Published on: June 25, 2019

Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques

Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques

Published on: June 30, 2020

相关概念视频

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...

Language and Cognition

Language and Cognition

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.