Resource-Efficient LLM Application for Structured Transformation of Unstructured Financial Contracts

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mridul, Maruf Ahmed, Seneviratne, Oshani
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909873495605248
author Mridul, Maruf Ahmed
Seneviratne, Oshani
author_facet Mridul, Maruf Ahmed
Seneviratne, Oshani
contents The transformation of unstructured legal contracts into standardized, machine-readable formats is essential for automating financial workflows. The Common Domain Model (CDM) provides a standardized framework for this purpose, but converting complex legal documents like Credit Support Annexes (CSAs) into CDM representations remains a significant challenge. In this paper, we present an extension of the CDMizer framework, a template-driven solution that ensures syntactic correctness and adherence to the CDM schema during contract-to-CDM conversion. We apply this extended framework to a real-world task, comparing its performance with a benchmark developed by the International Swaps and Derivatives Association (ISDA) for CSA clause extraction. Our results show that CDMizer, when integrated with a significantly smaller, open-source Large Language Model (LLM), achieves competitive performance in terms of accuracy and efficiency against larger, proprietary models. This work underscores the potential of resource-efficient solutions to automate legal contract transformation, offering a cost-effective and scalable approach that can meet the needs of financial institutions with constrained resources or strict data privacy requirements.
format Preprint
id arxiv_https___arxiv_org_abs_2510_23990
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Resource-Efficient LLM Application for Structured Transformation of Unstructured Financial Contracts
Mridul, Maruf Ahmed
Seneviratne, Oshani
Information Retrieval
The transformation of unstructured legal contracts into standardized, machine-readable formats is essential for automating financial workflows. The Common Domain Model (CDM) provides a standardized framework for this purpose, but converting complex legal documents like Credit Support Annexes (CSAs) into CDM representations remains a significant challenge. In this paper, we present an extension of the CDMizer framework, a template-driven solution that ensures syntactic correctness and adherence to the CDM schema during contract-to-CDM conversion. We apply this extended framework to a real-world task, comparing its performance with a benchmark developed by the International Swaps and Derivatives Association (ISDA) for CSA clause extraction. Our results show that CDMizer, when integrated with a significantly smaller, open-source Large Language Model (LLM), achieves competitive performance in terms of accuracy and efficiency against larger, proprietary models. This work underscores the potential of resource-efficient solutions to automate legal contract transformation, offering a cost-effective and scalable approach that can meet the needs of financial institutions with constrained resources or strict data privacy requirements.
title Resource-Efficient LLM Application for Structured Transformation of Unstructured Financial Contracts
topic Information Retrieval
url https://arxiv.org/abs/2510.23990