LAW: Legal Agentic Workflows for Custody and Fund Services Contracts
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916524935086080 |
|---|---|
| author | Watson, William Cho, Nicole Srishankar, Nishan Zeng, Zhen Cecchi, Lucas Scott, Daniel Siddagangappa, Suchetha Kaur, Rachneet Balch, Tucker Veloso, Manuela |
| author_facet | Watson, William Cho, Nicole Srishankar, Nishan Zeng, Zhen Cecchi, Lucas Scott, Daniel Siddagangappa, Suchetha Kaur, Rachneet Balch, Tucker Veloso, Manuela |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_11063 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LAW: Legal Agentic Workflows for Custody and Fund Services Contracts Watson, William Cho, Nicole Srishankar, Nishan Zeng, Zhen Cecchi, Lucas Scott, Daniel Siddagangappa, Suchetha Kaur, Rachneet Balch, Tucker Veloso, Manuela Artificial Intelligence Computation and Language Software Engineering 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. |
| title | LAW: Legal Agentic Workflows for Custody and Fund Services Contracts |
| topic | Artificial Intelligence Computation and Language Software Engineering |
| url | https://arxiv.org/abs/2412.11063 |