使用大型语言模型混合物进行零镜头机器生成文本检测

Matthieu Dubois, François Yvon, Pablo Piantanida
{"title":"使用大型语言模型混合物进行零镜头机器生成文本检测","authors":"Matthieu Dubois, François Yvon, Pablo Piantanida","doi":"arxiv-2409.07615","DOIUrl":null,"url":null,"abstract":"The dissemination of Large Language Models (LLMs), trained at scale, and\nendowed with powerful text-generating abilities has vastly increased the\nthreats posed by generative AI technologies by reducing the cost of producing\nharmful, toxic, faked or forged content. In response, various proposals have\nbeen made to automatically discriminate artificially generated from\nhuman-written texts, typically framing the problem as a classification problem.\nMost approaches evaluate an input document by a well-chosen detector LLM,\nassuming that low-perplexity scores reliably signal machine-made content. As\nusing one single detector can induce brittleness of performance, we instead\nconsider several and derive a new, theoretically grounded approach to combine\ntheir respective strengths. Our experiments, using a variety of generator LLMs,\nsuggest that our method effectively increases the robustness of detection.","PeriodicalId":501030,"journal":{"name":"arXiv - CS - Computation and Language","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Zero-Shot Machine-Generated Text Detection Using Mixture of Large Language Models\",\"authors\":\"Matthieu Dubois, François Yvon, Pablo Piantanida\",\"doi\":\"arxiv-2409.07615\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The dissemination of Large Language Models (LLMs), trained at scale, and\\nendowed with powerful text-generating abilities has vastly increased the\\nthreats posed by generative AI technologies by reducing the cost of producing\\nharmful, toxic, faked or forged content. In response, various proposals have\\nbeen made to automatically discriminate artificially generated from\\nhuman-written texts, typically framing the problem as a classification problem.\\nMost approaches evaluate an input document by a well-chosen detector LLM,\\nassuming that low-perplexity scores reliably signal machine-made content. As\\nusing one single detector can induce brittleness of performance, we instead\\nconsider several and derive a new, theoretically grounded approach to combine\\ntheir respective strengths. Our experiments, using a variety of generator LLMs,\\nsuggest that our method effectively increases the robustness of detection.\",\"PeriodicalId\":501030,\"journal\":{\"name\":\"arXiv - CS - Computation and Language\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-11\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Computation and Language\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.07615\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Computation and Language","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.07615","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

经过大规模训练并具备强大文本生成能力的大型语言模型(LLM)的传播,降低了制作有害、有毒、伪造或伪造内容的成本,从而大大增加了生成式人工智能技术带来的威胁。为此,人们提出了各种建议,以自动区分人工生成的文本和人类撰写的文本,通常将这一问题视为一个分类问题。大多数方法都是通过精心选择的检测器 LLM 来评估输入文档,并假设低复杂度分数是机器生成内容的可靠信号。由于使用单个检测器会导致性能脆性,我们转而考虑多个检测器,并推导出一种基于理论的新方法来结合它们各自的优势。我们使用各种生成器 LLM 进行的实验表明,我们的方法能有效提高检测的鲁棒性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Zero-Shot Machine-Generated Text Detection Using Mixture of Large Language Models
The dissemination of Large Language Models (LLMs), trained at scale, and endowed with powerful text-generating abilities has vastly increased the threats posed by generative AI technologies by reducing the cost of producing harmful, toxic, faked or forged content. In response, various proposals have been made to automatically discriminate artificially generated from human-written texts, typically framing the problem as a classification problem. Most approaches evaluate an input document by a well-chosen detector LLM, assuming that low-perplexity scores reliably signal machine-made content. As using one single detector can induce brittleness of performance, we instead consider several and derive a new, theoretically grounded approach to combine their respective strengths. Our experiments, using a variety of generator LLMs, suggest that our method effectively increases the robustness of detection.
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
自引率
0.00%
发文量
0
期刊最新文献
LLMs + Persona-Plug = Personalized LLMs MEOW: MEMOry Supervised LLM Unlearning Via Inverted Facts Extract-and-Abstract: Unifying Extractive and Abstractive Summarization within Single Encoder-Decoder Framework Development and bilingual evaluation of Japanese medical large language model within reasonably low computational resources Human-like Affective Cognition in Foundation Models
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1