论文概要
研究领域: ML 作者: Xinyan Ma, Xianhao Ou, Weihao Zhang 发布时间: 2025-04 arXiv: 2503.xxx1
中文摘要
知识图谱（KGs）是AI系统的关键基础，但其自动化构建不可避免地引入噪声，损害数据可信度。现有的三元组验证方法基于图嵌入或语言模型，往往因仅依赖内部结构约束或外部语义证据而遭受单源偏差，且通常遵循静态推理范式。因此，它们在处理复杂或长尾事实时遇到困难，并提供有限的解释性。为解决这些局限，我们提出了SHARP（Schema-Hybrid Agent for Reliable Prediction），一种无需训练的自主智能体，将三元组验证重构为战略规划、主动调查和证据推理的动态过程。具体而言，SHARP结合了记忆增强机制与模式感知战略规划以提高推理稳定性，并采用增强的ReAct循环与混合知识工具集，动态整合内部KG结构和外部文本证据进行交叉验证。在FB15K-237和Wikidata5M-Ind上的实验表明，SHARP显著优于现有最先进基线，分别实现4.2%和12.9%的准确率提升。此外，SHARP为每个判断提供透明、基于事实的证据链，展示了复杂验证任务的强解释性和鲁棒性。
原文摘要
Knowledge Graphs (KGs) serve as a critical foundation for AI systems, yet their automated construction inevitably introduces noise, compromising data trustworthiness. Existing triple verification methods, based on graph embeddings or language models, often suffer from single-source bias by relying on either internal structural constraints or external semantic evidence, and usually follow a static inference paradigm. As a result, they struggle with complex or long-tail facts and provide limited interpretability. To address these limitations, we propose SHARP (Schema-Hybrid Agent for Reliable Prediction), a training-free autonomous agent that reformulates triple verification as a dynamic process of strategic planning, active investigation, and evidential reasoning. Specifically, SHARP combin...
--- *自动采集于 2026-04-07*
#论文 #arXiv #ML #小凯 #自动采集