用智能体+检索生成自动筛查金融风险人物，误报率更低。
An Agentic LLM Framework for Adverse Media Screening in AML Compliance
- 构建多步智能体系统，结合网络搜索与文档处理
- 对高风险与低风险人物的识别准确率显著提升
- 适合金融机构合规团队快速筛查可疑人员
反洗钱（AML）与客户尽职调查（KYC）中，负面媒体报道筛查至关重要。传统方法依赖关键词搜索，易产生大量误报或需人工大量审核。本文提出一种基于大语言模型（LLM）与检索增强生成（RAG）的智能体系统，实现自动化负面媒体筛查。该系统通过多步骤流程：由LLM代理进行网络搜索、获取并处理相关文档，最终为每位主体计算一个负面媒体指数（AMI）得分。我们在包含政治敏感人物（PEPs）、监管观察名单人员、OpenSanctions制裁名单人员及学术来源的正常姓名数据集上，测试了多种LLM后端，验证了系统在区分高风险与低风险个体方面的有效性。
原文摘要 · Abstract (English)
Adverse media screening is a critical component of anti-money laundering (AML) and know-your-customer (KYC) compliance processes in financial institutions. Traditional approaches rely on keyword-based searches that generate high false-positive rates or require extensive manual review. We present an agentic system that leverages Large Language Models (LLMs) with Retrieval-Augmented Generation (RAG) to automate adverse media screening. Our system implements a multi-step approach where an LLM agent searches the web, retrieves and processes relevant documents, and computes an Adverse Media Index (AMI) score for each subject. We evaluate our approach using multiple LLM backends on a dataset comprising Politically Exposed Persons (PEPs), persons from regulatory watchlists, and sanctioned persons from OpenSanctions and clean names from academic sources, demonstrating the system's ability to distinguish between high-risk and low-risk individuals.
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。