CAAFC: Chronological Actionable Automated Fact-Checker for misinformation / non-factual hallucination detection and correction
Islam Eldifrawi, Shengrui Wang, Amine Trabelsi
TLDR
CAAFC is a new framework that automates fact-checking, detecting and correcting misinformation and AI hallucinations with actionable, source-backed justifications.
Key contributions
- Detects and corrects factual errors and AI hallucinations in claims, conversations, and dialogues.
- Provides actionable justifications for corrections, supported by primary information sources.
- Updates evidence and knowledge bases with recent and contextual information for reliability.
- Outperforms SOTA automated fact-checking and hallucination detection systems.
Why it matters
Existing automated fact-checking systems often misalign with real-world practices, struggling with the sheer volume of online content and AI hallucinations. CAAFC bridges these gaps by not only detecting but also correcting misinformation with verifiable sources, making it crucial for maintaining information integrity.
Original Abstract
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.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.