LAW: Legal Agentic Workflows for Custody and Fund Services Contracts
This addresses a domain-specific problem for legal professionals by providing a cost-effective alternative to fine-tuned LLMs, though it is incremental as it builds on existing agentic workflows.
The paper tackles the challenge of processing lengthy and complex legal contracts in custody and fund services using off-the-shelf LLMs, and introduces LAW, a modular system that outperforms baselines by 92.9% in tasks like calculating termination dates.
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.