用知识图谱让大模型可靠回答钢铁厂挥发性有机物治理问题
Traceable Knowledge Graph Reasoning Enables LLM-Assisted Decision Support for Industrial VOCs in the Steel Industry
- 构建2.7万节点、8万条关系的钢铁VOCs知识图谱，支持溯源问答
- 减少孤立节点至4.08%，准确率96.93%，专家评分1.69/2.00
- 适合环保工程师和工业决策者使用，避免大模型幻觉
钢铁行业挥发性有机物（VOCs）治理的关键知识分散在非结构化文献中，难以整合工艺、污染物与控制技术证据，通用大模型在回答低频工业问题时易产生幻觉。为此，我们开发了Chat-ISV——一种基于知识图谱（KG）的多智能体问答系统。该系统解析经筛选的钢铁行业VOCs文献语料库，构建包含27180个节点和81779条语义边的Neo4j知识图谱，融合提示约束提取、块中心拓扑优化、多智能体路由、来源回溯检索、本地文献检索、开放域知识接入及交互式子图可视化。基准测试与400次专家盲评显示，拓扑优化将孤立节点比例从57%降至4.08%，系统实现高事实可靠性：精确率96.93%，召回率72.63%，F1分数0.830，平均得分1.69/2.00。通过将零散的环境工程文献转化为可追溯、可查询、可支撑决策的知识体系，Chat-ISV为专用工业领域的大模型可靠部署与智能污染控制决策提供可扩展的信息学范式。
原文摘要 · Abstract (English)
Key knowledge for steel-industry volatile organic compounds (VOCs) governance is scattered across unstructured scientific literature, making it difficult to integrate process, pollutant, and control-technology evidence and increasing the risk of hallucination when general large language models (LLMs) answer low-frequency industrial questions. Here we developed Chat-ISV, a knowledge graph (KG) enhanced multi-agent Q&A system that parses a curated steel-industry VOCs literature corpus, constructs a Neo4j KG with 27180 nodes and 81779 semantic edges, and combines prompt-constrained extraction, chunk-centered topology optimization, multi-agent routing, source-backtracking retrieval, local literature retrieval, open-domain knowledge access, and interactive subgraph visualization. Benchmark tests and 400 expert blind evaluations showed that topology optimization reduced isolated nodes from 57% to 4.08% and that Chat-ISV achieved high factual reliability, with 96.93% precision, 72.63% recall, an F1-score of 0.830, and a mean score of 1.69/2.00. By converting fragmented environmental-engineering literature into traceable, queryable, and decision-support-oriented knowledge, Chat-ISV establishes a scalable environmental-informatics paradigm for reliable LLM deployment and intelligent pollution-control decision support in specialized industrial domains.
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。