使用大型语言模型生成合成数据,以提高基于BERT的神经网络的性能
Chancellor R Woolsey1, Prakash Bisht1, Joshua Rothman2
1University of Arizona, Tucson, Arizona.
概括
大型语言模型 (LLM) 可以生成合成患者数据用于训练机器学习 (ML) 模型. 这种对自闭症谱系障碍 (ASD) 数据创建的方法显示出希望,尽管它影响了模型精度.
科学领域:
- 医疗保健中的人工智能
- 临床信息学 临床信息学
- 生物医学数据科学 生物医学数据科学
背景情况:
- 医疗保健面临专家短缺,阻碍了患者查和诊断.
- 机器学习 (ML) 模型提供了潜在的解决方案,但需要大型,具有代表性的数据集.
- 数据集的创建是一个重要的瓶,因为高成本和资源需求.
研究的目的:
- 评估大型语言模型 (LLM) 对于生成合成医疗数据的实用性.
- 用LLM生成的行为示例来增强自闭症谱系障碍 (ASD) 的现有数据集.
- 用合成训练数据提高ML模型的准确性,以诊断患者.
主要方法:
- 促使GPT-3.5和GPT-4生成4,200个针对ASD的合成行为示例.
- 使用了经过生物医学文献预训练的BERT分类器来评估模型性能.
- 临床医生对LLM生成数据的一个子集 (N=140) 的评估.
主要成果:
- 临床审查表明,在LLM生成的行为示例-标签对中,准确率为83%.
- 通过合成数据增加培训数据集,模型召回率增加了13%.
- 数据集增强导致模型精度下降16%.
结论:
- 在医疗保健中,LLM显示出具有成本效益的合成数据生成潜力.
- 合成数据增强可以改善某些ML模型指标,如回忆.
- 需要进一步的研究来优化合成数据特征以改善ML结果.
更多相关视频
10:04Construction of an Improved Multi-Tetrode Hyperdrive for Large-Scale Neural Recording in Behaving Rats
Published on: May 9, 2018
11.3K
12:49Transcranial Direct Current Stimulation tDCS of Wernicke's and Broca's Areas in Studies of Language Learning and Word Acquisition
Published on: July 13, 2019
16.9K
相关概念视频
02:55Synthetic Biology
4.7K
Synthetic biology is an interdisciplinary science that involves using principles from disciplines such as engineering, molecular biology, cell biology, and systems biology. It involves remodeling existing organisms from nature or constructing completely new synthetic organisms for applications such as protein or enzyme production, bioremediation, value-added macromolecule production, and the addition of desirable traits to crops, to name a few.
Golden rice
Golden rice is a genetically modified...
Golden rice
Golden rice is a genetically modified...
4.7K
01:16Non-equilibrium in the Cell
4.4K
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...
4.4K