Vietnamese Legal Ontology 论文：将法律问答溯源到具体法条版本
Vietnamese Legal Ontology: Every legal answer, traced to the article that grounds it
越南团队用 NVIDIA Auto Ontology 流程把法律问答语料做成了可溯源的知识图谱。最有意思的是数据审计结果：36% 的引用指向已失效法律。做法律 RAG、知识图谱的人应该看看这套构建和验证方法。
越南研究团队基于 arXiv 发布 Vietnamese Legal Ontology 论文，将四个开放数据集构建为含 11.5M 节点、16.0M 边的法律知识图谱，流程遵循 NVIDIA Auto Ontology 的五个阶段（Discover、Ground、Validate、Expose、Learn）。该工作针对越南最大开放法律语料库的痛点：109,543 条问答配对 573,851 份法律文件，但引用是自由文本，如“本法第 101 条第 3 款”既不指明法律名称也不指明版本。
图谱中每个节点和边都携带来源记录与方法，无重复键、无悬空边、无 schema 违规。在 67,868 条被引用条款中，61,487 条解析到带日期的法律版本，51,694 条解析到具体的条、款、项，19,012 条实现逐字确认。
图谱还揭示了扁平数据隐藏的问题：78,361 条可解析引用的答案中 36% 引用了已失效法律；2,525 条验证过的引用指向的条文在现行法律中含义已变；2,520 条引用因措辞匹配了与日期不符的另一版本而需重新定版；5,575 个文件编号被多个地方机关共用，其中一个被 72 个机关共用。论文中所有数字均由图谱计算得出。
Vietnamese Legal Ontology: Every legal answer, traced to the article that grounds it
A legal answer is only as good as the article it rests on. Vietnam's largest open legal corpus pairs 109,543 published questions and answers with 573,851 legal documents, yet its citations are free text: "Khoan 3 Dieu 101 cua Bo luat nay" ("Clause 3, Article 101 of this Code") names neither the code nor its version. Following the five stages of NVIDIA Auto Ontology, Discover, Ground, Validate, Expose and Learn, we turn four open datasets into a knowledge graph of 11.5 M nodes and 16.0 M edges in which every node and edge carries its source record and method, with no duplicate keys, dangling edges or schema violations. Of 67,868 cited provisions, 61,487 resolve to a dated law version, 51,694 to a parsed article, clause or point, and 19,012 are confirmed word for word. The ontology then shows what flat records hide. 36% of the 78,361 answers whose citations resolve now cite a law that is no longer in force; 2,525 verified citations point to an article number that says something else in the current law; 2,520 citations were re-versioned because their words match a different version than their date suggests; and 5,575 document numbers are shared by several local authorities, one of them by 72. Every number in this paper is computed from the graph.
This report is categorized under AITOP's "Papers" desk, focusing on Southeast Asia and the ASEAN-6 (Singapore, Malaysia, Indonesia, Thailand, Vietnam, Philippines) digital economy. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Vietnamese Legal Ontology, NVIDIA Auto Ontology, 知识图谱, RAG.
Source attribution: curated from arXiv cs.AI (@Khac-Hoai Nam Bui, Quan Tran Minh).