相关实验视频

Updated: Jan 9, 2026

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

人工智能辅助的文献选:采用大型语言模型和检索增强生成的混合方法

Yiming Li¹, Xinsong Du¹, Yifei Wang²

¹Department of Medicine, Harvard Medical School, Boston, MA 02115, United States; Division of General Internal Medicine and Primary Care, Department of Medicine, Brigham and Women's Hospital, Boston, MA 02115, United States.

International journal of medical informatics

|December 1, 2025

概括

本研究引入了用于自动化文献选的大型语言模型 (LLM) 方法,显著提高了效率和准确性. 混合方法结合了检索增强生成 (RAG) 和组合策略,用于增强生物医学证据合成.

科学领域:

生物医学信息学生物医学信息学
医疗保健中的人工智能
医学文献分析医学文献分析

背景情况:

手动系统文献审查是耗时且难以扩展的.
大型语言模型 (LLM) 提供了自动化文献选的潜力.
开发高效准确的基于LLM的方法对于证据合成至关重要.

研究的目的:

通过基于LLM的方法提高文学选的效率和准确性.
探索基于规则的预处理,检索增强生成 (RAG) 和基于LLM的选组合策略.
评估不同LLM和提示技术在识别相关的生物医学文献中的表现.

主要方法:

开发了一个混合框架,将RAG提示与LLM分类结合起来.
在6331篇生物医学文章中评估了DeepSeek-V3,Deepseek-R1和GPT-4o,使用二进制,RAG和基于证明的提示.
优先召回以最大限度地增加相关研究的纳入,以及精度,特异性和NPV.
测试了与癌症免疫疗法和医学LLM相关的十个额外主题的概括性.

主要成果:

混合方法 (基于规则的预处理 + DeepSeek R1 + RAG提示) 实现了0.77的召回和1.00的NPV.
组合方法实现了完美的精度 (1.00),但在其他指标中表现相似,除了F1.1.
DeepSeek-R1表现出强大的概括性,F1得分最高 (0.93) 和准确性 (0.88) 在其他主题上.

结论:

基于LLM的方法整合了RAG提示和整体策略,显著提高了文献选的准确性和可扩展性.
这种方法为在生物医学研究中推进LLM驱动的证据合成提供了基础.
这些发现支持通过更有效的文献审查来改善临床决策支持.

关键词:

合唱团合唱团合唱团信息检索信息检索大型语言模型.文学选文学选快递工程是指快递的工程.提取增强生成的提取.

更多相关视频

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

相关概念视频

Non-equilibrium in the Cell

Non-equilibrium in the Cell

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...

Genetic Screens

Genetic Screens

Genetic screens are tools used to identify genes and mutations responsible for phenotypes of interest. Genetic screens help identify individuals or a group of people at risk of developing genetic diseases and help them with early intervention, targeted therapy, and reproductive options.
Forward genetic screens
Forward or “classical” genetic screens involve creating random mutations in an organism’s DNA using radiation, mutagens, or insertion of additional bases, which...

Improving Translational Accuracy

Improving Translational Accuracy