Automated fact-checking has been a challenging task for the research community. Past works tried various strategies, such as end-to-end training, retrieval-augmented generation, and prompt engineering, to build robust fact-checking systems. However, their accuracy has not been very high for real-world deployment. We, on the other hand, propose a simple yet effective strategy, where entailed justifications generated by LLMs are used to train encoder-only language models (ELMs) for fact-checking. We conducted a rigorous set of experiments, comparing our approach with recent works and various prompting and fine-tuning strategies to demonstrate the superiority of our approach. Additionally, we did quality analysis of model explanations, ablation studies, and error analysis to provide a comprehensive understanding of our approach.

翻译：自动事实核查一直是研究界面临的一项挑战性任务。以往研究尝试了多种策略，如端到端训练、检索增强生成和提示工程，以构建鲁棒的事实核查系统。然而，这些方法在实际部署中的准确性尚未达到理想水平。本研究提出了一种简单而有效的策略：利用大型语言模型生成的蕴含性论证来训练仅编码器语言模型（ELMs）进行事实核查。我们通过一系列严谨的实验，将本方法与近期研究及多种提示与微调策略进行比较，证明了本方法的优越性。此外，我们还进行了模型解释的质量分析、消融研究及错误分析，以提供对本方法的全面理解。