用知识图谱重构供应链网络，让大模型实时生成可解释的风险报告
Exploring Network-Knowledge Graph Duality: A Case Study in Agentic Supply Chain Risk Analysis
- 将供应链网络视为知识图谱，用中心性算法找关键风险路径
- 通过上下文壳技术把数字变成自然语言，让大模型读懂数据
- 无需微调或专用图数据库，即可实时生成有依据的分析结论
大型语言模型在处理金融风险中的多模态、网络化数据时面临挑战。标准检索增强生成方法过于简化关系，而专用模型成本高且静态。本文提出一种以大模型为中心的智能体框架，用于供应链风险分析。核心是利用网络与知识图谱之间的固有对偶性：将供应链网络视作知识图谱，借助结构网络科学原理进行检索。一个由网络中心性评分引导的图遍历器，能高效提取最具经济意义的风险路径。智能体架构协调图谱检索、数值因子表和新闻流数据。关键创新在于使用新颖的“上下文壳”——描述性模板，将原始数据嵌入自然语言，使量化信息完全可被大模型理解。该轻量级方法使模型能在不进行昂贵微调或依赖专用图数据库的情况下，实时生成简洁、可解释、上下文丰富的风险叙述。
原文摘要 · Abstract (English)
Large Language Models (LLMs) struggle with the complex, multi-modal, and network-native data underlying financial risk. Standard Retrieval-Augmented Generation (RAG) oversimplifies relationships, while specialist models are costly and static. We address this gap with an LLM-centric agent framework for supply chain risk analysis. Our core contribution is to exploit the inherent duality between networks and knowledge graphs (KG). We treat the supply chain network as a KG, allowing us to use structural network science principles for retrieval. A graph traverser, guided by network centrality scores, efficiently extracts the most economically salient risk paths. An agentic architecture orchestrates this graph retrieval alongside data from numerical factor tables and news streams. Crucially, it employs novel ``context shells'' -- descriptive templates that embed raw figures in natural language -- to make quantitative data fully intelligible to the LLM. This lightweight approach enables the model to generate concise, explainable, and context-rich risk narratives in real-time without costly fine-tuning or a dedicated graph database.
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。