Loading...
Enhancing FEVER-Style Claim Fact-Checking Against Wikipedia: A Diagnostic Taxonomy and a Generative Framework
Chernyavskiy, Anton Ilvovsky, Dmitry Nakov, Preslav
Chernyavskiy, Anton
Ilvovsky, Dmitry
Nakov, Preslav
Files
Loading...
s41598-025-89202-x.pdf
Adobe PDF, 2.79 MB
Supervisor
Department
Machine Learning
Embargo End Date
Type
Conference proceeding
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Fact-checking is a crucial yet challenging task that continues to gain importance. In an effort to address this issue, the FEVER large-scale dataset was developed to facilitate evidence-based fact-checking using Wikipedia as a reference. Despite numerous proposed approaches and evaluations on this dataset, a comprehensive understanding of the errors made by these approaches is still lacking. Here, we aim to bridge this gap. We introduce a diagnostic taxonomy and a generative framework to enhance FEVER-style fact-checking. We establish a taxonomy of errors and we construct a diagnostic dataset that enables the analysis of the errors made by state-of-the-art models as well as their distribution within the FEVER dataset. Additionally, we provide a set of prompts to generate examples within this taxonomy. Our experiments demonstrate promising results through the utilization of these generated examples for fine-tuning. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.
Citation
A. Chernyavskiy, D. Ilvovsky, and P. Nakov, “Enhancing FEVER-Style Claim Fact-Checking Against Wikipedia: A Diagnostic Taxonomy and a Generative Framework,” Lecture Notes in Computer Science, vol. 15572 LNCS, pp. 310–325, 2025, doi: 10.1007/978-3-031-88708-6_20
Source
Lecture Notes in Computer Science
Conference
47th European Conference on Information Retrieval, ECIR 2025
Keywords
Diagnostic Dataset, Diagnostic Taxonomy, Fact-checking, Natural Language Inference, Synthetic Data, Wikipedia
Subjects
Source
47th European Conference on Information Retrieval, ECIR 2025
Publisher
Springer Nature