用知识图谱生成对比问题，提升大模型事实核查能力
KG-CRAFT: Knowledge Graph-based Contrastive Reasoning with LLMs for Enhancing Automated Fact-checking
- 基于知识图谱构建对比问题，引导大模型聚焦证据
- 在两个真实数据集上达到最新最优性能
- 适合需要高精度自动核验的新闻与政策场景
事实核查是自动化事实核查系统的核心，旨在通过可靠证据源（如文档或知识库）判断陈述的真实性。本文提出KG-CRAFT，一种利用大语言模型（LLMs）并结合知识图谱生成对比问题的方法，以增强自动陈述验证。首先从陈述及其相关报告中构建知识图谱，再根据图结构生成上下文相关的对比问题。这些问题是证据报告提炼的引导工具，将其合成简洁摘要后交由大模型进行真伪评估。在两个真实世界数据集（LIAR-RAW 和 RAWFC）上的广泛实验表明，该方法在预测性能上达到新基准。全面分析验证了基于知识图谱的对比推理在提升大模型事实核查能力方面的有效性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。