How We Refute Claims: Automatic Fact-Checking through Flaw Identification and Explanation
This addresses the problem of complex real-world rumors and deceptive claims for internet content governance, representing a novel task rather than incremental improvement.
The paper tackles automated fact-checking by introducing a novel flaw-oriented approach that includes aspect generation and flaw identification, and presents RefuteClaim framework and FlawCheck dataset, showing effective classification and explanation of false claims.
Automated fact-checking is a crucial task in the governance of internet content. Although various studies utilize advanced models to tackle this issue, a significant gap persists in addressing complex real-world rumors and deceptive claims. To address this challenge, this paper explores the novel task of flaw-oriented fact-checking, including aspect generation and flaw identification. We also introduce RefuteClaim, a new framework designed specifically for this task. Given the absence of an existing dataset, we present FlawCheck, a dataset created by extracting and transforming insights from expert reviews into relevant aspects and identified flaws. The experimental results underscore the efficacy of RefuteClaim, particularly in classifying and elucidating false claims.