arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.00029cs.CLcs.AIcs.LG
收藏

构建、对齐与推理:面向企业知识管理的大型本体模型

Construct, Align, and Reason: Large Ontology Models for Enterprise Knowledge Management

Yonyou AI Lab(用友人工智能实验室);Yonyou Network Technology Co., Ltd.(用友网络技术有限公司)

Yao Zhang, Hongyin Zhu

AI总结:

本文提出大型本体模型(LOM),通过构建、对齐和推理框架,实现企业知识管理中多源异构数据的整合与复杂语义推理,实验表明其在复杂图推理任务中表现优于现有模型。

摘要:

企业级知识管理在整合多源异构数据和实现有效语义推理方面面临重大挑战。传统知识图谱在隐含关系发现上存在困难,并且缺乏对复杂问答的充分语义理解。为解决这些局限性,我们引入了一个统一的构建-对齐-推理框架,即大型本体模型(LOM)。我们首先从结构化数据库和非结构化文本中构建双层企业本体,随后将这些来源融合为一个综合的企业本体。为了实现指令对齐的推理,我们提出了一种统一的三阶段训练流程:本体指令微调以提高结构理解;文本-本体定位以加强节点语义编码;以及在本体-语言对上进行多任务指令微调,采用课程学习以增强语义推理和生成。我们还构建了涵盖多样本体推理任务的全面训练和评估数据集。在此基准上,我们的400亿参数LOM实现了89.47%的准确率,并在复杂图推理上优于DeepSeek-V3.2,表明了本体结构和语言的有效融合。

英文摘要:

Enterprise-scale knowledge management faces significant challenges in integrating multi-source heterogeneous data and enabling effective semantic reasoning. Traditional knowledge graphs often struggle with implicit relationship discovery and lack sufficient semantic understanding for complex question answering. To address these limitations, we introduce a unified construct--align--reason framework, the large ontology model (LOM). We first build a dual-layer enterprise ontology from structured databases and unstructured text, subsequently fusing these sources into a comprehensive enterprise ontology. To enable instruction-aligned reasoning, we propose a unified three-stage training pipeline: ontology instruction fine-tuning to improve structural understanding; text-ontology grounding to strengthen node semantic encoding; and multi-task instruction tuning on ontology-language pairs with curriculum learning to enhance semantic reasoning and generation. We also construct comprehensive training and evaluation datasets covering diverse ontology reasoning tasks. On this benchmark, our 4B-parameter LOM achieves 89.47% accuracy and outperforms DeepSeek-V3.2 on complex graph reasoning, indicating effective fusion of ontology structure and language.

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。

↑