LAW: Legal Agentic Workflows for Custody and Fund Services Contracts
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 strea...
Gespeichert in:
| Veröffentlicht in: | arXiv.org 2024-12 |
|---|---|
| Hauptverfasser: | , , , , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | arXiv.org |
| container_volume | |
| creator | Watson, William Cho, Nicole Srishankar, Nishan Zeng, Zhen Cecchi, Lucas Scott, Daniel Siddagangappa, Suchetha Kaur, Rachneet Balch, Tucker Veloso, Manuela |
| description | 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 | Article |
| fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_3145901042</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3145901042</sourcerecordid><originalsourceid>FETCH-proquest_journals_31459010423</originalsourceid><addsrcrecordid>eNqNissKgkAUQIcgSMp_uNBaGGe0104sadGuwKUMOoomc2vuTNHf56IPaHPO4pwZC4SUcbRLhFiwkGjgnIvNVqSpDNjxkpUHuOhOjZB12ri-hhLtvR3xTdCihdyTw-YDyjRQ-AlXbV99rQlyNM6q2tGKzVs1kg5_XrJ1cbrl5-hh8ek1uWpAb82UKhkn6Z7HPBHyv-sLsfU5lg</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3145901042</pqid></control><display><type>article</type><title>LAW: Legal Agentic Workflows for Custody and Fund Services Contracts</title><source>Open Access: Freely Accessible Journals by multiple vendors</source><creator>Watson, William ; Cho, Nicole ; Srishankar, Nishan ; Zeng, Zhen ; Cecchi, Lucas ; Scott, Daniel ; Siddagangappa, Suchetha ; Kaur, Rachneet ; Balch, Tucker ; Veloso, Manuela</creator><creatorcontrib>Watson, William ; Cho, Nicole ; Srishankar, Nishan ; Zeng, Zhen ; Cecchi, Lucas ; Scott, Daniel ; Siddagangappa, Suchetha ; Kaur, Rachneet ; Balch, Tucker ; Veloso, Manuela</creatorcontrib><description>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.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Contracts ; Large language models ; Legislation ; Modular design ; Task complexity ; Unstructured data</subject><ispartof>arXiv.org, 2024-12</ispartof><rights>2024. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>776,780</link.rule.ids></links><search><creatorcontrib>Watson, William</creatorcontrib><creatorcontrib>Cho, Nicole</creatorcontrib><creatorcontrib>Srishankar, Nishan</creatorcontrib><creatorcontrib>Zeng, Zhen</creatorcontrib><creatorcontrib>Cecchi, Lucas</creatorcontrib><creatorcontrib>Scott, Daniel</creatorcontrib><creatorcontrib>Siddagangappa, Suchetha</creatorcontrib><creatorcontrib>Kaur, Rachneet</creatorcontrib><creatorcontrib>Balch, Tucker</creatorcontrib><creatorcontrib>Veloso, Manuela</creatorcontrib><title>LAW: Legal Agentic Workflows for Custody and Fund Services Contracts</title><title>arXiv.org</title><description>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.</description><subject>Contracts</subject><subject>Large language models</subject><subject>Legislation</subject><subject>Modular design</subject><subject>Task complexity</subject><subject>Unstructured data</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNissKgkAUQIcgSMp_uNBaGGe0104sadGuwKUMOoomc2vuTNHf56IPaHPO4pwZC4SUcbRLhFiwkGjgnIvNVqSpDNjxkpUHuOhOjZB12ri-hhLtvR3xTdCihdyTw-YDyjRQ-AlXbV99rQlyNM6q2tGKzVs1kg5_XrJ1cbrl5-hh8ek1uWpAb82UKhkn6Z7HPBHyv-sLsfU5lg</recordid><startdate>20241215</startdate><enddate>20241215</enddate><creator>Watson, William</creator><creator>Cho, Nicole</creator><creator>Srishankar, Nishan</creator><creator>Zeng, Zhen</creator><creator>Cecchi, Lucas</creator><creator>Scott, Daniel</creator><creator>Siddagangappa, Suchetha</creator><creator>Kaur, Rachneet</creator><creator>Balch, Tucker</creator><creator>Veloso, Manuela</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20241215</creationdate><title>LAW: Legal Agentic Workflows for Custody and Fund Services Contracts</title><author>Watson, William ; Cho, Nicole ; Srishankar, Nishan ; Zeng, Zhen ; Cecchi, Lucas ; Scott, Daniel ; Siddagangappa, Suchetha ; Kaur, Rachneet ; Balch, Tucker ; Veloso, Manuela</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_31459010423</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Contracts</topic><topic>Large language models</topic><topic>Legislation</topic><topic>Modular design</topic><topic>Task complexity</topic><topic>Unstructured data</topic><toplevel>online_resources</toplevel><creatorcontrib>Watson, William</creatorcontrib><creatorcontrib>Cho, Nicole</creatorcontrib><creatorcontrib>Srishankar, Nishan</creatorcontrib><creatorcontrib>Zeng, Zhen</creatorcontrib><creatorcontrib>Cecchi, Lucas</creatorcontrib><creatorcontrib>Scott, Daniel</creatorcontrib><creatorcontrib>Siddagangappa, Suchetha</creatorcontrib><creatorcontrib>Kaur, Rachneet</creatorcontrib><creatorcontrib>Balch, Tucker</creatorcontrib><creatorcontrib>Veloso, Manuela</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</collection><collection>SciTech Premium Collection (Proquest) (PQ_SDU_P3)</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Watson, William</au><au>Cho, Nicole</au><au>Srishankar, Nishan</au><au>Zeng, Zhen</au><au>Cecchi, Lucas</au><au>Scott, Daniel</au><au>Siddagangappa, Suchetha</au><au>Kaur, Rachneet</au><au>Balch, Tucker</au><au>Veloso, Manuela</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>LAW: Legal Agentic Workflows for Custody and Fund Services Contracts</atitle><jtitle>arXiv.org</jtitle><date>2024-12-15</date><risdate>2024</risdate><eissn>2331-8422</eissn><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.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | EISSN: 2331-8422 |
| ispartof | arXiv.org, 2024-12 |
| issn | 2331-8422 |
| language | eng |
| recordid | cdi_proquest_journals_3145901042 |
| source | Open Access: Freely Accessible Journals by multiple vendors |
| subjects | Contracts Large language models Legislation Modular design Task complexity Unstructured data |
| title | LAW: Legal Agentic Workflows for Custody and Fund Services Contracts |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-22T20%3A34%3A24IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=LAW:%20Legal%20Agentic%20Workflows%20for%20Custody%20and%20Fund%20Services%20Contracts&rft.jtitle=arXiv.org&rft.au=Watson,%20William&rft.date=2024-12-15&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E3145901042%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3145901042&rft_id=info:pmid/&rfr_iscdi=true |