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

Improving Translational Accuracy02:07

Improving Translational Accuracy

2.7K
2.7K
Lagging Strand Synthesis01:59

Lagging Strand Synthesis

14.0K
14.0K
Small interfering RNAs (siRNA)02:30

Small interfering RNAs (siRNA)

3.6K
3.6K
lncRNA - Long Non-coding RNAs02:39

lncRNA - Long Non-coding RNAs

2.9K
2.9K
Lampbrush Chromosomes01:51

Lampbrush Chromosomes

2.5K
2.5K
Pre-mRNA Processing: RNA Splicing01:36

Pre-mRNA Processing: RNA Splicing

5.4K
5.4K

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

Growth charts for small sample sizes using unsupervised clustering: Application to canine early growth.

Veterinary research communications·2022
Same author

FlauBERT vs. CamemBERT: Understanding patient's answers by a French medical chatbot.

Artificial intelligence in medicine·2022
Same author

Case Report: True Motor Recovery of Upper Limb Beyond 5 Years Post-stroke.

Frontiers in neurology·2022
Same author

Effects of dataset size and interactions on the prediction performance of logistic regression and deep learning models.

Computer methods and programs in biomedicine·2021
Same author

T1/T2 ratio: A quantitative sensitive marker of brain tissue integrity in multiple sclerosis.

Journal of neuroimaging : official journal of the American Society of Neuroimaging·2021
Same author

Signal Intensity Evaluation in the Dentate Nucleus and Subcortical Gray Matter : Effect of Several Administrations of Gadoterate Meglumine in Multiple Sclerosis.

Clinical neuroradiology·2021
Same journal

Cross-linguistic patterns of cognitive biases in large language models: a comparative study in English, Hebrew, and Russian.

Frontiers in artificial intelligence·2026
Same journal

From human-like AI to user adoption: the role of trust, attitude, and social influence in shaping behavioral intention.

Frontiers in artificial intelligence·2026
Same journal

Building large-scale English-Romanian literary translation resources with open models.

Frontiers in artificial intelligence·2026
Same journal

Editorial: GenAI in healthcare: technologies, applications and evaluation.

Frontiers in artificial intelligence·2026
Same journal

Logic, inference, understanding: cross-domain generalization for generative language models.

Frontiers in artificial intelligence·2026
Same journal

Label tree semantic losses for rich multi-class medical image segmentation.

Frontiers in artificial intelligence·2026
查看所有相关文章

相关实验视频

Updated: Sep 11, 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

681

划分和总结:改善SLM文本总结方法.

Alexandre Bailly1, Antoine Saubin1, Gabriel Kocevar1

  • 1Seenovate, Paris, France.

Frontiers in artificial intelligence
|August 18, 2025
PubMed
概括
此摘要是机器生成的。

使用小语言模型 (SLM) 进行文本总结的地图方法有效地解决了"迷失在中间"的问题,并与大语言模型 (LLM) 的性能相匹配. 这种方法优于传统的"Stuff"方法,用于总结较短的文本.

关键词:
在中世纪迷失.自动评估的自动评估.小型语言模型.文本生成 文本生成文本总结 文本总结 文本总结

更多相关视频

Systematic Hearing Performance Evaluation Process for Adolescents with Cochlear Implantation at Early Ages
06:04

Systematic Hearing Performance Evaluation Process for Adolescents with Cochlear Implantation at Early Ages

Published on: March 24, 2023

471
Cloud-Based Phrase Mining and Analysis of User-Defined Phrase-Category Association in Biomedical Publications
09:20

Cloud-Based Phrase Mining and Analysis of User-Defined Phrase-Category Association in Biomedical Publications

Published on: February 23, 2019

8.8K

相关实验视频

Last Updated: Sep 11, 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

681
Systematic Hearing Performance Evaluation Process for Adolescents with Cochlear Implantation at Early Ages
06:04

Systematic Hearing Performance Evaluation Process for Adolescents with Cochlear Implantation at Early Ages

Published on: March 24, 2023

471
Cloud-Based Phrase Mining and Analysis of User-Defined Phrase-Category Association in Biomedical Publications
09:20

Cloud-Based Phrase Mining and Analysis of User-Defined Phrase-Category Association in Biomedical Publications

Published on: February 23, 2019

8.8K

科学领域:

  • 自然语言处理自然语言处理.
  • 人工智能的人工智能

背景情况:

  • 文本总结面临挑战,包括"迷失在中间"问题,模型忽略了长时间输入中的信息.
  • 大语言模型 (LLM) 和小语言模型 (SLM) 正在推进总结,但"迷失在中间"问题仍然存在.
  • 传统的"Stuff"总结方法在一次传递中处理文本,可能会丢失关键细节.

研究的目的:

  • 调查"地图"总结方法是否优于SLM上下文窗口中的文本的"Stuff"方法.
  • 评估"地图"方法在缓解"迷失在中间"问题的有效性.
  • 为了比较使用"地图"方法的SLM与使用"Stuff"方法的LLM的性能.

主要方法:

  • 一项由两部分组成的研究,涉及模拟生成文本和自动化事实检索评估.
  • 一个实践研究的重点是总结科学论文.
  • 使用SLMs和LLMs进行"地图"和"东西"总结方法的比较.

主要成果:

  • 在这两项研究中",地图"方法与"材料"方法相比,产生了同等或更高准确度的摘要.
  • "地图"方法表明,从文本的开头和中间保留了关键事实.
  • 采用"地图"方法的SLM实现了与使用"Stuff"方法的LLM可比的性能.

结论:

  • "地图"方法有效地解决了文本总结中的"迷失在中间"问题.
  • 对于SLM上下文窗口中的文本",地图"方法是比"东西"方法更有效的总结策略.
  • "地图"方法为文本总结提供了一个实用和高效的替代方案,特别是在SLM中.