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

Survival Tree01:19

Survival Tree

369
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
 Building a Survival Tree
Constructing a...
369
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving01:29

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

255
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...
255

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

Trefoil polymers from a knotted synthon.

Nature chemistry·2026
Same author

Symmetry-Protected Acoustic "Ghost Tunnels".

Physical review letters·2026
Same author

Increased risk of venous thromboembolism in children and teenagers with inflammatory bowel disease: a systematic review and meta-analysis.

PeerJ·2026
Same author

Assessment of Intraspecific Diversity and Screening of Elite Genotypes of <i>Atriplex canescens</i> as a Host Plant for <i>Cistanche deserticola</i>.

Plants (Basel, Switzerland)·2026
Same author

Waist circumference as a mediator in the association between sarcopenia and cognitive function.

Journal of Alzheimer's disease : JAD·2026
Same author

Correction to "Unlocking the Carbon Mitigation Potential of Green Infrastructure: Evidence from China's Sponge City Program".

Environmental science & technology·2026

相关实验视频

Updated: Jan 7, 2026

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

983

为环境复杂性利用LLM:结构化微调数据集和部署策略

Chuke Chen1, Nan Li1,2, Jianchuan Qi1

  • 1School of Environment, Tsinghua University, Beijing 100084, P. R. China.

Environmental science & technology
|January 1, 2026
PubMed
概括
此摘要是机器生成的。

生成型人工智能 (AI) 显示出对环境分析的前景. 一个分层的人工智能部署策略,将特定任务的微调模型和复杂决策的通用模型相结合,提供了一个可扩展的解决方案.

关键词:
代理工作流程的工作流程环境复杂性 环境复杂性精细调整 精细调整生成型的人工智能 (GAI)大型语言模型.

更多相关视频

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

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

Published on: June 13, 2025

1.2K

相关实验视频

Last Updated: Jan 7, 2026

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

983
Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

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

Published on: June 13, 2025

1.2K

科学领域:

  • 环境科学 环境科学
  • 人工智能的人工智能
  • 数据科学数据科学数据科学

背景情况:

  • 生成型人工智能 (AI),特别是大型语言模型 (LLM),有可能推进环境分析.
  • 部署的挑战包括有限的结构化领域知识和不清楚的决策策略.
  • 现有的人工智能模型在复杂的环境决策环境中缺乏适应性.

研究的目的:

  • 开发一个以中国为中心的环境知识数据集,用于LLM微调和基准测试.
  • 评估环境决策中微调和通用LLM之间的性能权衡.
  • 为环境情报中的LLM提出一个分层部署战略.

主要方法:

  • 建立基于教科书的,分层组织的环境知识数据集.
  • 对标准化环境任务的专用数据集进行微调LLM.
  • 在代理工作流程和决策任务中对微调模型与最先进的通用模型进行比较.
  • 在精度,响应效率,适应性和系统级可持续性方面评估模型性能.

主要成果:

  • 微调模型在标准化任务上显示了精度 (+1%) 和效率 (+52%) 的适度提高,但在代理工作流程中适应性有限 (-3%).
  • 在系统层面的可持续性和跨学科任务 (+10%) 中,通用主义模型的表现优于系统层面的可持续性和跨学科任务 (+10%),展示了卓越的跨领域推理和工具集成.
  • 在环境应用中,LLM的专业微调和广泛的适应性之间存在一种权衡.

结论:

  • 对于环境智能,建议采用分层的LLM部署策略.
  • 选择性微调适用于稳定,监管和验证任务.
  • 使用通用模型的代理工作流对动态,数据密集型和跨学科的决策有效.
  • 该研究提供了可重复使用的数据集和用于部署LLM作为环境决策支持工具的框架.