自动检测并修正虚假信息，支持动态更新知识库。
CAAFC: Chronological Actionable Automated Fact-Checker for misinformation / non-factual hallucination detection and correction
- 基于时间顺序与可操作性设计，贴近真实查证流程
- 在多个数据集上超越现有最先进水平，支持纠错与溯源
- 适合需要实时、可信内容审核的平台或机构使用
随着每小时上传内容量激增，以及生成式AI带来的幻觉问题，自动化事实核查（AFC）变得愈发关键，人工核查已无法应对信息洪流。专业核查人员指出，现有AFC系统与实际核查流程存在脱节。本文提出CAAFC（Chronological Actionable Automated Fact-Checker），一种旨在弥合这一差距的框架。它在多个基准数据集上优于当前最先进的事实核查与幻觉检测系统。CAAFC可处理声明、对话与多轮交流，不仅能识别事实错误与幻觉，还能提供基于原始信息源的可操作性解释以进行修正。此外，它可根据需要整合最新和上下文相关信息，动态更新证据与知识库，从而提升核查可靠性。
原文摘要 · Abstract (English)
With the vast amount of content uploaded every hour, along with the AI generated content that can include hallucinations, Automated Fact-Checking (AFC) has become increasingly vital, as it is infeasible for human fact-checkers to manually verify the sheer volume of information generated online. Professional fact-checkers have identified several gaps in existing AFC systems, noting a misalignment between how these systems operate and how fact-checking is performed in practice. In this paper, we introduce CAAFC (Chronological Actionable Automated Fact-Checker), a frame-work designed to bridge these gaps. It surpasses SOTA AFC and hallucination detection systems across multiple benchmark datasets. CAAFC operates on claims, conversations, and dialogues, enabling it not only to detect factual errors and hallucinations, but also to correct them by providing actionable justifications supported by primary information sources. Furthermore, CAAFC can update evidence and knowledge bases by incorporating recent and contextual information when necessary, thereby enhancing the reliability of fact verification.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。