Integrating Causal Reasoning into Automated Fact-Checking

TL;DR

This paper introduces a causal reasoning approach for automated fact-checking, improving the detection of logical inconsistencies and enhancing explainability by integrating event relations and rule-based analysis.

Contribution

It presents the first baseline method combining causal event relationships with fact-checking, addressing a gap in current approaches.

Findings

Improved detection of causal inconsistencies in claims.

Enhanced explainability of fact-checking decisions.

Established baseline performance on two datasets.

Abstract

In fact-checking applications, a common reason to reject a claim is to detect the presence of erroneous cause-effect relationships between the events at play. However, current automated fact-checking methods lack dedicated causal-based reasoning, potentially missing a valuable opportunity for semantically rich explainability. To address this gap, we propose a methodology that combines event relation extraction, semantic similarity computation, and rule-based reasoning to detect logical inconsistencies between chains of events mentioned in a claim and in an evidence. Evaluated on two fact-checking datasets, this method establishes the first baseline for integrating fine-grained causal event relationships into fact-checking and enhance explainability of verdict prediction.