RAGAR，你的虚假信息雷达：基于多模态大语言模型的RAG增强推理用于政治事实核查
RAGAR, Your Falsehood Radar: RAG-Augmented Reasoning for Political Fact-Checking using Multimodal Large Language Models
AI总结：
针对政治领域多模态错误信息核查难题，提出结合多模态大模型与RAG的RAGAR框架及CoRAG、ToRAG两种推理技术，加权F1达0.85，超基线0.14，人工评估显示多数生成解释覆盖金标准全部信息。
摘要：
错误信息尤其是政治话语中的错误信息带来的挑战日益严峻，亟需先进的事实核查方案，这在更复杂的多模态声明场景中尤为突出。我们将多模态大语言模型与检索增强生成（RAG）结合来解决该问题，并提出两种新型推理技术：Chain of RAG（CoRAG，RAG链）和Tree of RAG（ToRAG，RAG树）。它们通过提取文本与图像内容、检索外部信息，并基于已有证据推理后续待解答问题，来对多模态声明进行事实核查。我们取得了0.85的加权F1值，比基线推理技术高出0.14个点。人工评估证实，我们生成的绝大多数事实核查解释包含了金标准数据中的全部信息。
英文摘要：
The escalating challenge of misinformation, particularly in political discourse, requires advanced fact-checking solutions; this is even clearer in the more complex scenario of multimodal claims. We tackle this issue using a multimodal large language model in conjunction with retrieval-augmented generation (RAG), and introduce two novel reasoning techniques: Chain of RAG (CoRAG) and Tree of RAG (ToRAG). They fact-check multimodal claims by extracting both textual and image content, retrieving external information, and reasoning subsequent questions to be answered based on prior evidence. We achieve a weighted F1-score of 0.85, surpassing a baseline reasoning technique by 0.14 points. Human evaluation confirms that the vast majority of our generated fact-check explanations contain all information from gold standard data.
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。
