An Agentic LLM Framework for Adverse Media Screening in AML Compliance
This addresses the issue of high false-positive rates and manual review in financial compliance for institutions, representing an incremental improvement over traditional keyword-based methods.
The paper tackles the problem of adverse media screening in AML compliance by presenting an agentic LLM framework with RAG to automate the process, demonstrating its ability to distinguish between high-risk and low-risk individuals on a dataset including PEPs, watchlists, and clean names.
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.