AI4Contracts: LLM & RAG-Powered Encoding of Financial Derivative Contracts

TL;DR

This paper presents CDMizer, a novel framework combining LLMs and RAG for structured extraction and validation of financial contracts, enhancing scalability and accuracy in document understanding.

Contribution

Introduction of CDMizer, a template-driven, hierarchical LLM and RAG-based system for structured text transformation and validation of financial derivatives.

Findings

Effective transformation of OTC contracts into CDM schema

Improved scalability and schema adherence in structured extraction

Validated framework with an LLM-powered evaluation method

Abstract

Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) are reshaping how AI systems extract and organize information from unstructured text. A key challenge is designing AI methods that can incrementally extract, structure, and validate information while preserving hierarchical and contextual relationships. We introduce CDMizer, a template-driven, LLM, and RAG-based framework for structured text transformation. By leveraging depth-based retrieval and hierarchical generation, CDMizer ensures a controlled, modular process that aligns generated outputs with predefined schema. Its template-driven approach guarantees syntactic correctness, schema adherence, and improved scalability, addressing key limitations of direct generation methods. Additionally, we propose an LLM-powered evaluation framework to assess the completeness and accuracy of structured representations. Demonstrated in the transformation of Over-the-Counter (OTC) financial derivative contracts into the Common Domain Model (CDM), CDMizer establishes a scalable foundation for AI-driven document understanding, structured synthesis, and automated validation in broader contexts.