Integrating Causal Reasoning into Automated Fact-Checking
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908712499675136 |
|---|---|
| author | Rebboud, Youssra Lisena, Pasquale Troncy, Raphael |
| author_facet | Rebboud, Youssra Lisena, Pasquale Troncy, Raphael |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_13286 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Integrating Causal Reasoning into Automated Fact-Checking Rebboud, Youssra Lisena, Pasquale Troncy, Raphael Computation and Language I.2.7 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. |
| title | Integrating Causal Reasoning into Automated Fact-Checking |
| topic | Computation and Language I.2.7 |
| url | https://arxiv.org/abs/2512.13286 |