Integrating Causal Reasoning into Automated Fact-Checking
This work addresses the need for more explainable and semantically rich fact-checking systems, though it is incremental as it builds on existing methods to incorporate causal analysis.
The paper tackled the problem of missing causal reasoning in automated fact-checking by proposing a method that integrates event relation extraction, semantic similarity, and rule-based reasoning to detect logical inconsistencies in claims, establishing the first baseline for this approach on two datasets.
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.