区分人类写作和机器生成的科学论文的基准数据集

IF 2.4 Q3 COMPUTER SCIENCE, INFORMATION SYSTEMS
Mohamed Hesham Ibrahim Abdalla, Simon Malberg, Daryna Dementieva, Edoardo Mosca, Georg Groh
{"title":"区分人类写作和机器生成的科学论文的基准数据集","authors":"Mohamed Hesham Ibrahim Abdalla, Simon Malberg, Daryna Dementieva, Edoardo Mosca, Georg Groh","doi":"10.3390/info14100522","DOIUrl":null,"url":null,"abstract":"As generative NLP can now produce content nearly indistinguishable from human writing, it is becoming difficult to identify genuine research contributions in academic writing and scientific publications. Moreover, information in machine-generated text can be factually wrong or even entirely fabricated. In this work, we introduce a novel benchmark dataset containing human-written and machine-generated scientific papers from SCIgen, GPT-2, GPT-3, ChatGPT, and Galactica, as well as papers co-created by humans and ChatGPT. We also experiment with several types of classifiers—linguistic-based and transformer-based—for detecting the authorship of scientific text. A strong focus is put on generalization capabilities and explainability to highlight the strengths and weaknesses of these detectors. Our work makes an important step towards creating more robust methods for distinguishing between human-written and machine-generated scientific papers, ultimately ensuring the integrity of scientific literature.","PeriodicalId":38479,"journal":{"name":"Information (Switzerland)","volume":"9 1","pages":"0"},"PeriodicalIF":2.4000,"publicationDate":"2023-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A Benchmark Dataset to Distinguish Human-Written and Machine-Generated Scientific Papers\",\"authors\":\"Mohamed Hesham Ibrahim Abdalla, Simon Malberg, Daryna Dementieva, Edoardo Mosca, Georg Groh\",\"doi\":\"10.3390/info14100522\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"As generative NLP can now produce content nearly indistinguishable from human writing, it is becoming difficult to identify genuine research contributions in academic writing and scientific publications. Moreover, information in machine-generated text can be factually wrong or even entirely fabricated. In this work, we introduce a novel benchmark dataset containing human-written and machine-generated scientific papers from SCIgen, GPT-2, GPT-3, ChatGPT, and Galactica, as well as papers co-created by humans and ChatGPT. We also experiment with several types of classifiers—linguistic-based and transformer-based—for detecting the authorship of scientific text. A strong focus is put on generalization capabilities and explainability to highlight the strengths and weaknesses of these detectors. Our work makes an important step towards creating more robust methods for distinguishing between human-written and machine-generated scientific papers, ultimately ensuring the integrity of scientific literature.\",\"PeriodicalId\":38479,\"journal\":{\"name\":\"Information (Switzerland)\",\"volume\":\"9 1\",\"pages\":\"0\"},\"PeriodicalIF\":2.4000,\"publicationDate\":\"2023-09-26\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Information (Switzerland)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.3390/info14100522\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"COMPUTER SCIENCE, INFORMATION SYSTEMS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Information (Switzerland)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3390/info14100522","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
引用次数: 0

摘要

由于生成式NLP现在可以产生与人类写作几乎没有区别的内容,因此在学术写作和科学出版物中识别真正的研究贡献变得越来越困难。此外,机器生成文本中的信息在事实上可能是错误的,甚至完全是捏造的。在这项工作中,我们引入了一个新的基准数据集,其中包含来自SCIgen, GPT-2, GPT-3, ChatGPT和卡拉狄加的人类编写和机器生成的科学论文,以及人类和ChatGPT共同创建的论文。我们还实验了几种类型的分类器——基于语言的和基于转换的——用于检测科学文本的作者身份。重点放在泛化能力和可解释性上,以突出这些检测器的优点和缺点。我们的工作朝着创建更强大的方法来区分人类写作和机器生成的科学论文迈出了重要的一步,最终确保了科学文献的完整性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
A Benchmark Dataset to Distinguish Human-Written and Machine-Generated Scientific Papers
As generative NLP can now produce content nearly indistinguishable from human writing, it is becoming difficult to identify genuine research contributions in academic writing and scientific publications. Moreover, information in machine-generated text can be factually wrong or even entirely fabricated. In this work, we introduce a novel benchmark dataset containing human-written and machine-generated scientific papers from SCIgen, GPT-2, GPT-3, ChatGPT, and Galactica, as well as papers co-created by humans and ChatGPT. We also experiment with several types of classifiers—linguistic-based and transformer-based—for detecting the authorship of scientific text. A strong focus is put on generalization capabilities and explainability to highlight the strengths and weaknesses of these detectors. Our work makes an important step towards creating more robust methods for distinguishing between human-written and machine-generated scientific papers, ultimately ensuring the integrity of scientific literature.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Information (Switzerland)
Information (Switzerland) Computer Science-Information Systems
CiteScore
6.90
自引率
0.00%
发文量
515
审稿时长
11 weeks
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信