arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2510.01115cs.AIcs.MAecon.THphysics.soc-ph
收藏

探索网络-知识图谱二元性:代理供应链风险分析的案例研究

Exploring Network-Knowledge Graph Duality: A Case Study in Agentic Supply Chain Risk Analysis

University of California, Berkeley(加州大学伯克利分校)

Evan Heus, Rick Bookstaber, Dhruv Sharma

AI总结:

本文提出基于LLM的代理框架,利用网络与知识图谱的二元性,通过图遍历和上下文壳技术实现供应链风险分析的实时可解释生成。

摘要:

大型语言模型(LLMs)在处理金融风险背后的复杂、多模态和网络原生数据时面临困难。标准的检索增强生成(RAG)方法过于简化了关系,而专门模型成本高且静态。我们通过一个以LLM为核心的代理框架来解决这一差距,用于供应链风险分析。我们的核心贡献是利用网络和知识图谱(KG)之间固有的二元性。我们将供应链网络视为一个知识图谱,允许我们使用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,高效地提取出最经济显著的风险路径。一个代理架构协调这一图检索与数值因子表和新闻流的数据。关键的是,它使用新的“上下文壳”——将原始数字嵌入自然语言的描述模板——使定量数据对LLM完全可理解。这种轻量级方法使模型能够实时生成简洁、可解释且具有上下文丰富性的风险叙述,而无需昂贵的微调或专用图数据库。

英文摘要:

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.

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。

↑