使用知识驱动推理检测被操纵内容
Detecting Manipulated Contents Using Knowledge-Grounded Inference
AI总结：
本文提出Manicod工具，通过RAG技术结合LLM推理，利用实时检索的上下文信息检测零日被操纵内容，并在包含4270条假新闻的数据集上取得0.856的F1分数，显著优于现有方法。
摘要：
被操纵内容的检测作为假新闻的一种普遍形式，近年来已被广泛研究。尽管现有解决方案在基于历史事件进行事实核查和分析假新闻方面已被证明有效，但它们依赖于训练期间获得的内在知识或人工策划的上下文，这阻碍了它们应对零日被操纵内容，此类内容只能通过实时上下文信息来识别。在本研究中，我们提出了Manicod，一种用于检测零日被操纵内容的工具。Manicod首先从主流搜索引擎获取关于输入主张的上下文信息，随后通过检索增强生成（RAG）为大型语言模型（LLM）对上下文进行向量化。基于LLM的推理能够产生“真实”或“被操纵”的决策，并为该决策提供文本解释。为验证Manicod的有效性，我们还提出了一个数据集，包含4270条源自2500条近期真实世界新闻标题的被操纵假新闻。Manicod在该数据集上实现了0.856的总体F1分数，并在其事实核查和主张验证基准上的F1分数比现有方法高出最多1.9倍。
英文摘要：
The detection of manipulated content, a prevalent form of fake news, has been widely studied in recent years. While existing solutions have been proven effective in fact-checking and analyzing fake news based on historical events, the reliance on either intrinsic knowledge obtained during training or manually curated context hinders them from tackling zero-day manipulated content, which can only be recognized with real-time contextual information. In this work, we propose Manicod, a tool designed for detecting zero-day manipulated content. Manicod first sources contextual information about the input claim from mainstream search engines, and subsequently vectorizes the context for the large language model (LLM) through retrieval-augmented generation (RAG). The LLM-based inference can produce a "truthful" or "manipulated" decision and offer a textual explanation for the decision. To validate the effectiveness of Manicod, we also propose a dataset comprising 4270 pieces of manipulated fake news derived from 2500 recent real-world news headlines. Manicod achieves an overall F1 score of 0.856 on this dataset and outperforms existing methods by up to 1.9x in F1 score on their benchmarks on fact-checking and claim verification.
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。
