CORRECT：用于事实核查的上下文与参考文献增强推理及提示
CORRECT: Context- and Reference-Augmented Reasoning and Prompting for Fact-Checking
AI总结：
针对证据句缺乏自足上下文的问题，提出CORRECT方法，通过三层证据图、层内跨层推理及证据条件提示编码提升事实核查性能。
摘要：
核查声明的真实性通常需要对多个证据句进行推理。很多时候，证据句并不总是自足的，可能需要来自其他地方的额外上下文和参考文献，才能理解共指表达、缩写以及所报告发现的适用范围。例如，学术论文中的证据句可能需要该论文中的上下文句子及其引用论文中的描述，以确定一项研究发现的范围。然而，大多数事实核查模型主要关注证据句内部的推理，而忽略了辅助上下文和参考文献。为解决这一问题，我们提出了一种新方法，即上下文与参考文献增强推理及提示。对于证据推理，我们构建了包含证据层、上下文层和参考文献层的三层证据图。我们设计了层内和跨层推理，将三个图层整合为统一的证据嵌入。对于判定预测，我们设计了证据条件提示编码器，为每个声明生成独特的提示嵌入。这些证据条件提示嵌入与声明被统一起来用于事实核查。实验验证了我们模型的优势。
英文摘要：
Fact-checking the truthfulness of claims usually requires reasoning over multiple evidence sentences. Oftentimes, evidence sentences may not be always self-contained, and may require additional contexts and references from elsewhere to understand coreferential expressions, acronyms, and the scope of a reported finding. For example, evidence sentences from an academic paper may need contextual sentences in the paper and descriptions in its cited papers to determine the scope of a research discovery. However, most fact-checking models mainly focus on the reasoning within evidence sentences, and ignore the auxiliary contexts and references. To address this problem, we propose a novel method, Context- and Reference-augmented Reasoning and Prompting. For evidence reasoning, we construct a three-layer evidence graph with evidence, context, and reference layers. We design intra- and cross-layer reasoning to integrate three graph layers into a unified evidence embedding. For verdict prediction, we design evidence-conditioned prompt encoder, which produces unique prompt embeddings for each claim. These evidence-conditioned prompt embeddings and claims are unified for fact-checking. Experiments verify the strength of our model.
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。
