arXiv 2502.165142025-05-28cs.CL

GraphCheck：利用提取的知识图谱驱动的打破长文本壁垒的事实核查

GraphCheck: Breaking Long-Term Text Barriers with Extracted Knowledge Graph-Powered Fact-Checking

University of Tokyo（东京大学）；Texas A&M University（德克萨斯A&M大学）；University of Cambridge（剑桥大学）；Duke-NUS Medical School（杜克-新加坡国立大学医学院）；Aarhus University（阿贾克斯大学）；Yale University（耶鲁大学）

Yingjian Chen, Haoran Liu, Yinhong Liu, Jinxiang Xie, Rui Yang, Han Yuan, Yanran Fu, Peng Yuan Zhou, Qingyu Chen, James Caverlee, Irene Li

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对长文本事实核查中多跳关系理解难和成对比较成本高的问题，提出 GraphCheck 框架，利用提取的知识图谱和图神经网络作为软提示增强 LLMs，在单次推理中捕获多跳推理链，在七个基准上提升 7.1%，性能媲美最先进模型且参数更少。

摘要：

大型语言模型（LLMs）被广泛使用，但它们经常产生细微的事实错误，尤其是在长文本中。这些错误在医学等专业领域是致命的。现有的基于接地文档的事实核查方法面临两个主要挑战：（1）它们难以理解长文档中复杂的多跳关系，经常忽略细微的事实错误；（2）大多数专业方法依赖成对比较，需要多次模型调用，导致高资源和计算成本。为了应对这些挑战，我们提出了 GraphCheck，这是一个使用提取的知识图谱来增强文本表示的事实核查框架。图神经网络进一步处理这些图作为软提示，使 LLMs 能够更有效地整合结构化知识。通过基于图的推理增强，GraphCheck 捕获了现有方法经常忽略的多跳推理链，从而在单次推理调用中实现精确且高效的事实核查。在跨越通用和医学领域的七个基准上的实验结果表明，相比基线模型有高达 7.1% 的整体提升。值得注意的是，GraphCheck 优于现有的专业事实核查器，并以显著更少的参数实现了与 DeepSeek-V3 和 OpenAI-o1 等最先进 LLMs 相当的性能。

英文摘要：

Large language models (LLMs) are widely used, but they often generate subtle factual errors, especially in long-form text. These errors are fatal in some specialized domains such as medicine. Existing fact-checking with grounding documents methods face two main challenges: (1) they struggle to understand complex multihop relations in long documents, often overlooking subtle factual errors; (2) most specialized methods rely on pairwise comparisons, requiring multiple model calls, leading to high resource and computational costs. To address these challenges, we propose GraphCheck, a fact-checking framework that uses extracted knowledge graphs to enhance text representation. Graph Neural Networks further process these graphs as a soft prompt, enabling LLMs to incorporate structured knowledge more effectively. Enhanced with graph-based reasoning, GraphCheck captures multihop reasoning chains that are often overlooked by existing methods, enabling precise and efficient fact-checking in a single inference call. Experimental results on seven benchmarks spanning both general and medical domains demonstrate up to a 7.1% overall improvement over baseline models. Notably, GraphCheck outperforms existing specialized fact-checkers and achieves comparable performance with state-of-the-art LLMs, such as DeepSeek-V3 and OpenAI-o1, with significantly fewer parameters.

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。