融合知识图谱、大模型与搜索代理，提升事实核查的准确与可解释性。
Hybrid Fact-Checking that Integrates Knowledge Graphs, Large Language Models, and Search-Based Retrieval Agents Improves Interpretable Claim Verification
- 分三步：先查知识图谱，再用大模型分类，最后不足时调用网络搜索。
- 在FEVER数据集上达0.93的F1分数，无需微调即可实现高精度。
- 适合需要可解释性验证的场景，尤其对‘信息不足’的判断有改进能力。
大语言模型（LLM）虽能生成流畅文本，但缺乏可靠的事实依据。基于知识图谱的事实核查虽精准可解释，但覆盖有限或延迟较高。本文提出一种混合核查方法，融合知识图谱、大模型与实时搜索代理，充分发挥各组件优势。系统包含三个自主步骤：1）在DBpedia中进行快速单跳检索；2）使用任务专用提示词的大模型分类，输出带有内部规则逻辑的结果；3）当知识图谱覆盖不足时，调用网络搜索代理。该流程在不进行任务微调的情况下，于FEVER基准的支持/反驳划分上达到0.93的F1分数。为应对‘信息不足’情况，我们开展定向重标注研究，结果显示本方法常能发现原标记为‘信息不足’的陈述的有效证据，经专家与大模型评审确认。本文提供模块化、开源的事实核查流水线，具备回退策略并可在多数据集上泛化。
原文摘要 · Abstract (English)
Large language models (LLMs) excel in generating fluent utterances but can lack reliable grounding in verified information. At the same time, knowledge-graph-based fact-checkers deliver precise and interpretable evidence, yet suffer from limited coverage or latency. By integrating LLMs with knowledge graphs and real-time search agents, we introduce a hybrid fact-checking approach that leverages the individual strengths of each component. Our system comprises three autonomous steps: 1) a Knowledge Graph (KG) Retrieval for rapid one-hop lookups in DBpedia, 2) an LM-based classification guided by a task-specific labeling prompt, producing outputs with internal rule-based logic, and 3) a Web Search Agent invoked only when KG coverage is insufficient. Our pipeline achieves an F1 score of 0.93 on the FEVER benchmark on the Supported/Refuted split without task-specific fine-tuning. To address Not enough information cases, we conduct a targeted reannotation study showing that our approach frequently uncovers valid evidence for claims originally labeled as Not Enough Information (NEI), as confirmed by both expert annotators and LLM reviewers. With this paper, we present a modular, opensource fact-checking pipeline with fallback strategies and generalization across datasets.
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。