SUCEA：通过声明分解与编辑实现对抗性事实核查的推理密集型检索
SUCEA: Reasoning-Intensive Retrieval for Adversarial Fact-checking through Claim Decomposition and Editing
AI总结：
SUCEA框架通过声明分解、迭代证据检索与编辑及证据聚合三个步骤，无需训练即可提升对抗性事实核查的检索与蕴含标签准确率，在两个数据集上优于四个基线方法。
摘要：
自动事实核查作为对抗虚假信息的手段，近年来受到越来越多的关注。尽管取得了显著进展，基于检索增强语言模型的事实核查系统仍然难以应对对抗性声明，这类声明由人类故意设计，旨在挑战事实核查系统。为了解决这些挑战，我们提出了一种无需训练的方法，旨在改写原始声明，使其更容易定位支持证据。我们的模块化框架SUCEA将任务分解为三个步骤：1）声明分割与去语境化，将对抗性声明分割为独立的子声明；2）迭代证据检索与声明编辑，迭代地检索证据并根据检索到的证据编辑子声明；3）证据聚合与标签预测，聚合所有检索到的证据并预测蕴含标签。在两个具有挑战性的事实核查数据集上的实验表明，我们的框架在检索准确率和蕴含标签准确率上均有显著提升，优于四个强大的基于声明分解的基线方法。
英文摘要：
Automatic fact-checking has recently received more attention as a means of combating misinformation. Despite significant advancements, fact-checking systems based on retrieval-augmented language models still struggle to tackle adversarial claims, which are intentionally designed by humans to challenge fact-checking systems. To address these challenges, we propose a training-free method designed to rephrase the original claim, making it easier to locate supporting evidence. Our modular framework, SUCEA, decomposes the task into three steps: 1) Claim Segmentation and Decontextualization that segments adversarial claims into independent sub-claims; 2) Iterative Evidence Retrieval and Claim Editing that iteratively retrieves evidence and edits the subclaim based on the retrieved evidence; 3) Evidence Aggregation and Label Prediction that aggregates all retrieved evidence and predicts the entailment label. Experiments on two challenging fact-checking datasets demonstrate that our framework significantly improves on both retrieval and entailment label accuracy, outperforming four strong claim-decomposition-based baselines.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
