CAAFC: Chronological Actionable Automated Fact-Checker for misinformation / non-factual hallucination detection and correction

TL;DR

The paper introduces CAAFC, an advanced automated fact-checking framework that detects and corrects misinformation and hallucinations in various content types, surpassing existing systems in accuracy and providing actionable justifications.

Contribution

CAAFC is a novel framework that bridges gaps in current AFC systems by enabling detection, correction, and updating of factual information across diverse content formats.

Findings

Surpasses state-of-the-art AFC and hallucination detection systems.

Operates effectively on claims, conversations, and dialogues.

Provides actionable justifications supported by primary sources.

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.