迈向更安全的网络：多语言多智能体大语言模型用于缓解对抗性错误信息攻击
Toward a Safer Web: Multilingual Multi-Agent LLMs for Mitigating Adversarial Misinformation Attacks
AI总结：
本文提出一个多语言多智能体大语言模型框架，结合检索增强生成，作为网页插件部署，以缓解跨语言切换、查询膨胀和结构重排等对抗性错误信息攻击，保护在线事实完整性。
摘要：
数字平台上错误信息的快速传播威胁着公共话语、情绪稳定和决策制定。虽然先前的工作已探索了错误信息检测中的各种对抗性攻击，但本文所研究的特定转换尚未被系统性地研究。具体而言，我们研究了跨英语、法语、西班牙语、阿拉伯语、印地语和中文的语言切换，随后进行翻译。我们还研究了在摘要化之前进行的查询长度膨胀，以及将结构重排为多项选择题。在本文中，我们提出了一个多语言、多智能体的大语言模型框架，该框架结合了检索增强生成，可部署为在线平台的网页插件。我们的工作强调了AI驱动的错误信息检测在保护在线事实完整性免受各种攻击方面的重要性，同时展示了基于插件的部署在真实世界网络应用中的可行性。
英文摘要：
The rapid spread of misinformation on digital platforms threatens public discourse, emotional stability, and decision-making. While prior work has explored various adversarial attacks in misinformation detection, the specific transformations examined in this paper have not been systematically studied. In particular, we investigate language-switching across English, French, Spanish, Arabic, Hindi, and Chinese, followed by translation. We also study query length inflation preceding summarization and structural reformatting into multiple-choice questions. In this paper, we present a multilingual, multi-agent large language model framework with retrieval-augmented generation that can be deployed as a web plugin into online platforms. Our work underscores the importance of AI-driven misinformation detection in safeguarding online factual integrity against diverse attacks, while showcasing the feasibility of plugin-based deployment for real-world web applications.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
