基于知识图谱的对比推理：利用大语言模型增强自动事实核查
KG-CRAFT: Knowledge Graph-based Contrastive Reasoning with LLMs for Enhancing Automated Fact-checking
AI总结：
KG-CRAFT通过结合知识图谱和大语言模型，提升自动事实核查的准确性与性能。
摘要：
声明验证是自动事实核查系统的核心组成部分，旨在通过评估与可靠证据来源（如文档或知识库）对比来确定陈述的真实性。本文提出了KG-CRAFT，一种利用大语言模型（LLMs）并结合基于知识图谱的对比问题来提高自动声明验证的方法。KG-CRAFT首先从声明和相关报告中构建知识图谱，然后根据知识图谱的结构制定上下文相关的对比问题。这些问题指导证据报告的提炼，这些报告被综合成简明的摘要，用于LLMs的可信度评估。在两个真实世界数据集（LIAR-RAW和RAWFC）上的广泛评估表明，我们的方法在预测性能上达到了新的状态-of-the-art。全面的分析验证了我们的基于知识图谱的对比推理方法在提升LLMs事实核查能力方面的有效性。
英文摘要：
Claim verification is a core component of automated fact-checking systems, aimed at determining the truthfulness of a statement by assessing it against reliable evidence sources such as documents or knowledge bases. This work presents KG-CRAFT, a method that improves automatic claim verification by leveraging large language models (LLMs) augmented with contrastive questions grounded in a knowledge graph. KG-CRAFT first constructs a knowledge graph from claims and associated reports, then formulates contextually relevant contrastive questions based on the knowledge graph structure. These questions guide the distillation of evidence-based reports, which are synthesised into a concise summary that is used for veracity assessment by LLMs. Extensive evaluations on two real-world datasets (LIAR-RAW and RAWFC) demonstrate that our method achieves a new state-of-the-art in predictive performance. Comprehensive analyses validate in detail the effectiveness of our knowledge graph-based contrastive reasoning approach in improving LLMs' fact-checking capabilities.
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。
