arXiv 2506.074462025-06-09cs.AI

碎片化事实：通过基于 LLM 的原子事实提取与验证解构复杂声明

Fact in Fragments: Deconstructing Complex Claims via LLM-based Atomic Fact Extraction and Verification

Key Laboratory of Trustworthy Distributed Computing and Service (MoE)（可信分布式计算与服务重点实验室）；Beijing Academy of Artificial Intelligence（北京人工智能研究院）；Jinan University（暨南大学）；Department of Gastric Surgery, Clinical Oncology School of Fujian Medical University, Fujian Cancer Hospital(Fujian Branch of Fudan University Shanghai Cancer Center)（福建医科大学胃外科临床肿瘤学院、福建肿瘤医院（复旦大学上海肿瘤中心福建分部））

Liwen Zheng, Chaozhuo Li, Zheng Liu, Feiran Huang, Haoran Jia, Zaisheng Ye, Xi Zhang

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对复杂声明多跳验证中的静态分解、噪声证据和错误传播问题，提出 AFEV 框架，通过迭代原子事实提取、证据重排和上下文示例推理提升准确性与可解释性。

摘要：

事实验证通过证据检索和推理评估声明的真实性，在打击虚假信息方面发挥着关键作用。然而，传统方法难以处理需要针对碎片化证据进行多跳推理的复杂声明，因为它们通常依赖静态分解策略和表层语义检索，无法捕捉声明的细微结构与意图。这会导致推理错误累积、噪声证据污染，以及对多样声明的适应性有限，最终损害复杂场景下的验证准确性。为解决该问题，我们提出 Atomic Fact Extraction and Verification（AFEV，原子事实提取与验证），这是一种新颖框架，通过迭代方式将复杂声明分解为原子事实，从而实现细粒度检索和自适应推理。AFEV 通过迭代事实提取动态细化对声明的理解并减少错误传播，对证据重新排序以过滤噪声，并利用特定上下文示例指导推理过程。在五个基准数据集上的大量实验表明，AFEV 在准确性和可解释性方面均达到最先进性能。

英文摘要：

Fact verification plays a vital role in combating misinformation by assessing the veracity of claims through evidence retrieval and reasoning. However, traditional methods struggle with complex claims requiring multi-hop reasoning over fragmented evidence, as they often rely on static decomposition strategies and surface-level semantic retrieval, which fail to capture the nuanced structure and intent of the claim. This results in accumulated reasoning errors, noisy evidence contamination, and limited adaptability to diverse claims, ultimately undermining verification accuracy in complex scenarios. To address this, we propose Atomic Fact Extraction and Verification (AFEV), a novel framework that iteratively decomposes complex claims into atomic facts, enabling fine-grained retrieval and adaptive reasoning. AFEV dynamically refines claim understanding and reduces error propagation through iterative fact extraction, reranks evidence to filter noise, and leverages context-specific demonstrations to guide the reasoning process. Extensive experiments on five benchmark datasets demonstrate that AFEV achieves state-of-the-art performance in both accuracy and interpretability.

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。