LAW: Legal Agentic Workflows for Custody and Fund Services Contracts

TL;DR

LAW introduces a modular system that uses specialized tools and agents to effectively interpret complex custody and fund services contracts, outperforming baseline models in key legal tasks.

Contribution

The paper presents LAW, a novel modular framework that integrates domain-specific tools and agents to improve legal contract analysis with large language models.

Findings

LAW outperforms baseline in complex legal tasks by 92.9% points.

It offers a cost-effective alternative to fine-tuned legal LLMs.

LAW effectively handles lengthy, complex legal texts.

Abstract

Legal contracts in the custody and fund services domain govern critical aspects such as key provider responsibilities, fee schedules, and indemnification rights. However, it is challenging for an off-the-shelf Large Language Model (LLM) to ingest these contracts due to the lengthy unstructured streams of text, limited LLM context windows, and complex legal jargon. To address these challenges, we introduce LAW (Legal Agentic Workflows for Custody and Fund Services Contracts). LAW features a modular design that responds to user queries by orchestrating a suite of domain-specific tools and text agents. Our experiments demonstrate that LAW, by integrating multiple specialized agents and tools, significantly outperforms the baseline. LAW excels particularly in complex tasks such as calculating a contract's termination date, surpassing the baseline by 92.9% points. Furthermore, LAW offers a cost-effective alternative to traditional fine-tuned legal LLMs by leveraging reusable, domain-specific tools.