Taxonomy-Aligned Risk Extraction from 10-K Filings with Autonomous Improvement Using LLMs

TL;DR

This paper introduces a novel LLM-based method for extracting structured risk factors from 10-K filings, ensuring taxonomy alignment and autonomous system improvement, validated on a large dataset with meaningful industry-related risk similarities.

Contribution

It presents a three-stage extraction pipeline combined with autonomous taxonomy maintenance, enabling continuous improvement and accurate risk factor extraction from financial documents.

Findings

Extracted 10,688 risk factors from S&P 500 companies.

Achieved 104.7% improvement in embedding separation through autonomous refinement.

Confirmed taxonomy captures meaningful economic structure with higher risk similarity within industries.

Abstract

We present a methodology for extracting structured risk factors from corporate 10-K filings while maintaining adherence to a predefined hierarchical taxonomy. Our three-stage pipeline combines LLM extraction with supporting quotes, embedding-based semantic mapping to taxonomy categories, and LLM-as-a-judge validation that filters spurious assignments. To evaluate our approach, we extract 10,688 risk factors from S&P 500 companies and examine risk profile similarity across industry clusters. Beyond extraction, we introduce autonomous taxonomy maintenance where an AI agent analyzes evaluation feedback to identify problematic categories, diagnose failure patterns, and propose refinements, achieving 104.7% improvement in embedding separation in a case study. External validation confirms the taxonomy captures economically meaningful structure: same-industry companies exhibit 63% higher risk profile similarity than cross-industry pairs (Cohen's d=1.06, AUC 0.82, p<0.001). The methodology generalizes to any domain requiring taxonomy-aligned extraction from unstructured text, with autonomous improvement enabling continuous quality maintenance and enhancement as systems process more documents.