Reasoning for fact verification using language models
| dc.contributor.advisor | Ghorbani, Ali A. | |
| dc.contributor.author | Kanaani, Mohammadamin | |
| dc.date.accessioned | 2024-05-08T19:55:17Z | |
| dc.date.available | 2024-05-08T19:55:17Z | |
| dc.date.issued | 2024-02 | |
| dc.description.abstract | In response to the proliferation of misinformation on social media platforms, this thesis introduces the Triple-R framework (Retriever, Ranker, Reasoner) to enhance fact-checking by leveraging the Web for evidence retrieval and generating understandable explanations for its decisions. Unlike existing methods, Triple-R incorporates external sources for evidence and provides explanations for datasets lacking them. By fine-tuning a causal language model, it produces natural language explanations and labels for evidence-claim pairs, aiming for greater transparency and interpretability in fact-checking systems. Evaluated on a popular dataset, Triple-R achieved a state-of-the-art accuracy of 42.72% on the LIAR benchmark, outperforming current automated fact verification methods. This underscores its effectiveness in integrating web sources and offering clear reasons, presenting a significant step forward in the fight against online misinformation. | |
| dc.description.copyright | © Mohammadamin Kanaani, 2024 | |
| dc.format.extent | xviii, 139 | |
| dc.format.medium | electronic | |
| dc.identifier.uri | https://unbscholar.lib.unb.ca/handle/1882/37806 | |
| dc.language.iso | en | |
| dc.publisher | University of New Brunswick | |
| dc.rights | http://purl.org/coar/access_right/c_abf2 | |
| dc.subject.discipline | Computer Science | |
| dc.title | Reasoning for fact verification using language models | |
| dc.type | master thesis | |
| oaire.license.condition | other | |
| thesis.degree.discipline | Computer Science | |
| thesis.degree.grantor | University of New Brunswick | |
| thesis.degree.level | masters | |
| thesis.degree.name | M.C.S. |