真相侦探与趋势扭转者：用于核查 YouTube 视频事实并影响观点的 AI 智能体
Truth Sleuth and Trend Bender: AI Agents to fact-check YouTube videos and influence opinions
AI总结：
本文提出由 Truth Sleuth 和 Trend Bender 两个 AI 智能体组成的系统，通过 RAG 事实核查 YouTube 视频陈述并生成说服性评论，以打击错误信息并影响用户观点。
摘要：
错误信息在当今数字世界中构成重大威胁，往往通过 YouTube 等平台迅速传播。本文提出了一种应对错误信息的新方法，即开发一个由 AI 驱动的系统，该系统不仅核查 YouTube 视频中所作陈述的事实，还积极在评论区与用户互动并挑战误导性叙事。我们的系统包含两个主要智能体：Truth Sleuth 和 Trend Bender。Truth Sleuth 从 YouTube 视频中提取陈述，采用检索增强生成（Retrieval-Augmented Generation，RAG）方法——利用 Wikipedia、Google Search、Google FactCheck 等来源——准确评估其真实性，并生成一份细致而全面的报告。通过严格的提示工程，Trend Bender 利用该报告以及精心整理的语料库中的相关文章，生成富有洞见且具有说服力的评论，旨在激发富有成效的辩论。借助精心设置的自评估循环，该智能体能够迭代改进其风格并优化其输出。我们通过在既有基准数据集上的实验以及在 YouTube 上的真实部署展示了该系统的能力，表明其具有吸引用户并可能影响观点的潜力。我们的研究结果凸显了事实核查智能体的高准确性，并证实了 AI 驱动的干预措施在打击错误信息和营造更知情的网络空间方面的潜力。
英文摘要：
Misinformation poses a significant threat in today's digital world, often spreading rapidly through platforms like YouTube. This paper introduces a novel approach to combating misinformation by developing an AI-powered system that not only fact-checks claims made in YouTube videos but also actively engages users in the comment section and challenge misleading narratives. Our system comprises two main agents: Truth Sleuth and Trend Bender. Truth Sleuth extracts claims from a YouTube video, uses a Retrieval-Augmented Generation (RAG) approach - drawing on sources like Wikipedia, Google Search, Google FactCheck - to accurately assess their veracity and generates a nuanced and comprehensive report. Through rigorous prompt engineering, Trend Bender leverages this report along with a curated corpus of relevant articles to generate insightful and persuasive comments designed to stimulate a productive debate. With a carefully set up self-evaluation loop, this agent is able to iteratively improve its style and refine its output. We demonstrate the system's capabilities through experiments on established benchmark datasets and a real-world deployment on YouTube, showcasing its potential to engage users and potentially influence perspectives. Our findings highlight the high accuracy of our fact-checking agent, and confirm the potential of AI-driven interventions in combating misinformation and fostering a more informed online space.
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。
