用知识图谱自动构建企业环保数据结构，让监管文件变可机器读取的规范数据。
OntoMetric: An Ontology-Driven LLM-Assisted Framework for Automated ESG Metric Knowledge Graph Generation
- 以本体为约束，结合大模型与规则验证，从监管文件中提取合规的环保数据关系
- 在五大标准上实现超80%结构合规率，语义准确率达65%-90%，远超无约束方法
- 适合金融、审计等需自动化处理环境数据的机构，支持溯源与成本可控的批量生成
环境、社会与治理（ESG）指标知识具有内在结构，通过组成依赖关联行业、报告框架、指标类别、具体指标及计算模型，但实践中该结构仅隐含于SASB、TCFD、IFRS S2等监管文件中，极少以显式、受控或可机器操作的形式存在。现有ESG本体定义了正式模式，但无法从权威来源规模化构建与管理；而直接使用大语言模型（LLM）抽取常导致语义错误、虚构关系和结构无效。OntoMetric是一种基于本体引导的自动化框架，用于从监管文件生成可治理的ESG指标知识图谱（ESGMKG），将本体作为第一类约束嵌入抽取与填充流程。该框架融合结构感知分段、带语义字段与确定性标识符的本体约束型LLM抽取，以及两阶段验证——语义类型校验与基于规则的模式检查，并保留段落级与页面级溯源信息，确保可追溯至原始文本。在五个ESG监管标准上的评估显示，本体引导抽取的语义准确率达65%-90%，结构合规率超80%，相比无约束基线的3%-10%大幅提升，且每验证实体成本仅为0.01-0.02美元，效率提升48倍。
原文摘要 · Abstract (English)
Environmental, Social, and Governance (ESG) metric knowledge is inherently structured, connecting industries, reporting frameworks, metric categories, metrics, and calculation models through compositional dependencies, yet in practice this structure remains embedded implicitly in regulatory documents such as SASB, TCFD, and IFRS S2 and rarely exists as an explicit, governed, or machine-actionable artefact. Existing ESG ontologies define formal schemas but do not address scalable population and governance from authoritative regulatory sources, while unconstrained large language model (LLM) extraction frequently produces semantically incorrect entities, hallucinated relationships, and structurally invalid graphs. OntoMetric is an ontology-guided framework for the automated construction and governance of ESG metric knowledge graphs from regulatory documents that operationalises the ESG Metric Knowledge Graph (ESGMKG) ontology as a first-class constraint embedded directly into the extraction and population process. The framework integrates structure-aware segmentation, ontology-constrained LLM extraction enriched with semantic fields and deterministic identifiers, and two-phase validation combining semantic type verification with rule-based schema checking, while preserving segment-level and page-level provenance to ensure traceability to regulatory source text. Evaluation on five ESG regulatory standards shows that ontology-guided extraction achieves 65-90 percent semantic accuracy and over 80 percent schema compliance, compared with 3-10 percent for unconstrained baseline extraction, and yields stable cost efficiency with a cost per validated entity of 0.01-0.02 USD and a 48 times efficiency improvement over baseline.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。