FACT-GPT：利用大语言模型通过声明匹配进行事实核查增强
FACT-GPT: Fact-Checking Augmentation via Claim Matching with LLMs
AI总结：
FACT-GPT利用大语言模型自动化事实核查中的声明匹配，在合成数据上训练，能识别与已辟谣声明一致、矛盾或无关的内容，其准确性与更大模型相当并接近人类判断。
摘要：
我们的社会正面临猖獗的错误信息，这些信息危害公共健康和信任。为了应对这一社会挑战，我们引入了FACT-GPT，一个利用大语言模型（LLMs）来自动化事实核查中声明匹配阶段的系统。FACT-GPT在合成数据集上训练，能够识别与先前已辟谣声明一致、矛盾或无关的社交媒体内容。我们的评估表明，我们专门化的LLMs在识别相关声明方面能够匹配更大模型的准确性，并密切反映人类判断。这项研究为高效的声明匹配提供了一种自动化解决方案，展示了LLMs在支持事实核查人员方面的潜力，并为该领域的进一步研究提供了宝贵资源。
英文摘要：
Our society is facing rampant misinformation harming public health and trust. To address the societal challenge, we introduce FACT-GPT, a system leveraging Large Language Models (LLMs) to automate the claim matching stage of fact-checking. FACT-GPT, trained on a synthetic dataset, identifies social media content that aligns with, contradicts, or is irrelevant to previously debunked claims. Our evaluation shows that our specialized LLMs can match the accuracy of larger models in identifying related claims, closely mirroring human judgment. This research provides an automated solution for efficient claim matching, demonstrates the potential of LLMs in supporting fact-checkers, and offers valuable resources for further research in the field.
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。
