基于大语言模型的自动声明匹配：赋能事实核查员对抗错误信息
Automated Claim Matching with Large Language Models: Empowering Fact-Checkers in the Fight Against Misinformation
AI总结：
本研究提出FACT-GPT框架，利用大语言模型自动化事实核查中的声明匹配阶段，通过GPT-4生成训练数据微调专用模型，在公共卫生数据集上达到与大型预训练模型相当的性能，并提供公开资源。
摘要：
在当今数字时代，错误信息的快速传播对公共福祉和社会信任构成威胁。随着在线错误信息的激增，事实核查员的人工验证变得越来越具有挑战性。我们引入了FACT-GPT（面向声明匹配任务的事实核查增强生成式预训练Transformer），这是一个利用大语言模型（LLMs）自动化事实核查中声明匹配阶段的框架。该框架识别新的社交媒体内容，这些内容要么支持要么反驳事实核查员先前揭穿的声明。我们的方法采用GPT-4生成一个由模拟社交媒体帖子组成的标注数据集。该数据集作为微调更专门的LLMs的训练基础。我们在一个与公共卫生相关的大量社交媒体内容数据集上评估了FACT-GPT。结果表明，我们微调的LLMs在声明匹配任务上的表现可与更大的预训练LLMs相媲美，并与人工标注高度一致。本研究实现了三个关键里程碑：提供了一个增强事实核查的自动化框架；展示了LLMs补充人类专业知识的潜力；提供了公共资源，包括数据集和模型，以促进事实核查领域的进一步研究和应用。
英文摘要：
In today's digital era, the rapid spread of misinformation poses threats to public well-being and societal trust. As online misinformation proliferates, manual verification by fact checkers becomes increasingly challenging. We introduce FACT-GPT (Fact-checking Augmentation with Claim matching Task-oriented Generative Pre-trained Transformer), a framework designed to automate the claim matching phase of fact-checking using Large Language Models (LLMs). This framework identifies new social media content that either supports or contradicts claims previously debunked by fact-checkers. Our approach employs GPT-4 to generate a labeled dataset consisting of simulated social media posts. This data set serves as a training ground for fine-tuning more specialized LLMs. We evaluated FACT-GPT on an extensive dataset of social media content related to public health. The results indicate that our fine-tuned LLMs rival the performance of larger pre-trained LLMs in claim matching tasks, aligning closely with human annotations. This study achieves three key milestones: it provides an automated framework for enhanced fact-checking; demonstrates the potential of LLMs to complement human expertise; offers public resources, including datasets and models, to further research and applications in the fact-checking domain.
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。
