区分ChatGPT ((-3.5, -4) 产生的和人类撰写的论文,通过日本的风度分析
1Department of Psychological Counselling, Faculty of Psychology, Mejiro University, Tokyo, Japan.
PloS one
|August 9, 2023
概括
这项研究分析了来自ChatGPT (GPT-3.5和GPT-4) 和人类的日语文本,并使用了笔法特征. 一个随机的森林分类器在区分人工智能生成的和人类写的日文文本方面取得了100%的准确性.
科学领域:
- 自然语言处理自然语言处理.
- 计算语言学 计算语言学
- 人工智能的人工智能
背景情况:
- 像ChatGPT一样,文本生成人工智能迅速获得了全球关注.
- 了解人工智能生成文本的独特特征至关重要.
研究的目的:
- 为了比较由ChatGPT (GPT-3.5和GPT-4) 生成的文本与人类撰写的文本的日语造型特征.
- 评估机器学习分类器在区分人工智能和人类日语文本方面的有效性.
主要方法:
- 分析日本的造型学特征,包括部分语音大图,后定位粒子大图,逗号使用和函数词率.
- 应用多维缩放 (MDS) 来可视化文本分布.
- 训练和测试一个随机森林 (RF) 分类器用于文本分类.
主要成果:
- 在所有分析的笔法特征中,MDS揭示了GPT和人类文本的明显分布.
- 虽然GPT-4比GPT-3.5更先进,但它们的文本分布显示重叠.
- 射频分类器实现了高性能,达到100%的准确性,回忆,精度和F1得分,在使用所有风度特征将文本分类为由GPT生成或人类编写时.
- 专注于函数词的速度的射频分类器实现了98.1%的准确性.
结论:
- 造型仪的特征可以有效地区分人写和GPT生成的日文文本.
- 目前的人工智能生成的文本,尽管取得了进展,但在日本书法学中与人类写作有明显的差异.
- 人类目前可以高准确地区分ChatGPT生成的文本和人类写的日语文本.
相关概念视频
02:07Improving Translational Accuracy
2.6K
2.6K
01:35Pedigree Analysis
84.5K
Overview
84.5K
01:11Genetic Lingo
103.2K
Overview
103.2K
01:02Quantifying and Rejecting Outliers: The Grubbs Test
1.7K
Sometimes, a data set can have a recorded numerical observation that greatly deviates from the rest of the data. Assuming that the data is normally distributed, a statistical method called the Grubbs test can be used to determine whether the observation is truly an outlier. To perform a two-tailed Grubbs test, first, calculate the absolute difference between the outlier and the mean. Then, calculate the ratio between this difference and the standard deviation of the sample. This...
1.7K
01:11Statistical Analysis: Overview
6.7K
When we take repeated measurements on the same or replicated samples, we will observe inconsistencies in the magnitude. These inconsistencies are called errors. To categorize and characterize these results and their errors, the researcher can use statistical analysis to determine the quality of the measurements and/or suitability of the methods.
One of the most commonly used statistical quantifiers is the mean, which is the ratio between the sum of the numerical values of all results and the...
One of the most commonly used statistical quantifiers is the mean, which is the ratio between the sum of the numerical values of all results and the...
6.7K
02:46Chi-square Analysis
38.4K
The chi-square test is a statistical hypothesis test. It is used to check whether there is a significant difference between an expected value and an observed value. In the context of genetics, it enables us to either accept or reject a hypothesis, based on how much the observed values deviate from the expected values.
The chi-square test was developed by Pearson in 1990.
The first step of performing a Chi-square analysis is to establish a null hypothesis, which assumes that there is no real...
The chi-square test was developed by Pearson in 1990.
The first step of performing a Chi-square analysis is to establish a null hypothesis, which assumes that there is no real...
38.4K