@inproceedings{martinez-etal-2025-scalable,
title = "A Scalable Framework for Legal Text Understanding in Regulatory and Financial Contexts.",
author = "Mart{\'i}nez, Santiago and
Casta{\~n}eda, Juan Manuel and
Manrique, Ruben",
editor = "Chen, Chung-Chi and
Moreno-Sandoval, Antonio and
Huang, Jimin and
Xie, Qianqian and
Ananiadou, Sophia and
Chen, Hsin-Hsi",
booktitle = "Proceedings of the Joint Workshop of the 9th Financial Technology and Natural Language Processing (FinNLP), the 6th Financial Narrative Processing (FNP), and the 1st Workshop on Large Language Models for Finance and Legal (LLMFinLegal)",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.finnlp-1.39/",
pages = "326--334",
abstract = "This study presents a comprehensive approach to developing a domain-specific large language model (LLM) for regulatory and financial text interpretation. A specialized corpus was constructed through large-scale scraping of financial and regulatory documents across domains such as compliance, licensing, and financial reporting. The data was preprocessed using GPT-4o-mini with prompt engineering to retain critical information and remove noise. We further pre-trained a LLaMA-3.1-8B model on the curated corpus and fine-tuned it using an instruction dataset covering nine tasks from the Coling 2025 Regulations Challenge, including acronym expansion, regulatory question-answering, and XBRL-based financial analytics, employing QLoRA to reduce memory requirements. The model exhibits a slight improvement from baseline answering complex regulatory questions (detailed QA) and expanding acronyms. This study demonstrates the potential of domain-specific LLMs in regulatory text interpretation and lays the groundwork for future research in specialized NLP evaluation methodologies."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="martinez-etal-2025-scalable">
<titleInfo>
<title>A Scalable Framework for Legal Text Understanding in Regulatory and Financial Contexts.</title>
</titleInfo>
<name type="personal">
<namePart type="given">Santiago</namePart>
<namePart type="family">Martínez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="given">Manuel</namePart>
<namePart type="family">Castañeda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruben</namePart>
<namePart type="family">Manrique</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Joint Workshop of the 9th Financial Technology and Natural Language Processing (FinNLP), the 6th Financial Narrative Processing (FNP), and the 1st Workshop on Large Language Models for Finance and Legal (LLMFinLegal)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chung-Chi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Moreno-Sandoval</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jimin</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qianqian</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This study presents a comprehensive approach to developing a domain-specific large language model (LLM) for regulatory and financial text interpretation. A specialized corpus was constructed through large-scale scraping of financial and regulatory documents across domains such as compliance, licensing, and financial reporting. The data was preprocessed using GPT-4o-mini with prompt engineering to retain critical information and remove noise. We further pre-trained a LLaMA-3.1-8B model on the curated corpus and fine-tuned it using an instruction dataset covering nine tasks from the Coling 2025 Regulations Challenge, including acronym expansion, regulatory question-answering, and XBRL-based financial analytics, employing QLoRA to reduce memory requirements. The model exhibits a slight improvement from baseline answering complex regulatory questions (detailed QA) and expanding acronyms. This study demonstrates the potential of domain-specific LLMs in regulatory text interpretation and lays the groundwork for future research in specialized NLP evaluation methodologies.</abstract>
<identifier type="citekey">martinez-etal-2025-scalable</identifier>
<location>
<url>https://aclanthology.org/2025.finnlp-1.39/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>326</start>
<end>334</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Scalable Framework for Legal Text Understanding in Regulatory and Financial Contexts.
%A Martínez, Santiago
%A Castañeda, Juan Manuel
%A Manrique, Ruben
%Y Chen, Chung-Chi
%Y Moreno-Sandoval, Antonio
%Y Huang, Jimin
%Y Xie, Qianqian
%Y Ananiadou, Sophia
%Y Chen, Hsin-Hsi
%S Proceedings of the Joint Workshop of the 9th Financial Technology and Natural Language Processing (FinNLP), the 6th Financial Narrative Processing (FNP), and the 1st Workshop on Large Language Models for Finance and Legal (LLMFinLegal)
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F martinez-etal-2025-scalable
%X This study presents a comprehensive approach to developing a domain-specific large language model (LLM) for regulatory and financial text interpretation. A specialized corpus was constructed through large-scale scraping of financial and regulatory documents across domains such as compliance, licensing, and financial reporting. The data was preprocessed using GPT-4o-mini with prompt engineering to retain critical information and remove noise. We further pre-trained a LLaMA-3.1-8B model on the curated corpus and fine-tuned it using an instruction dataset covering nine tasks from the Coling 2025 Regulations Challenge, including acronym expansion, regulatory question-answering, and XBRL-based financial analytics, employing QLoRA to reduce memory requirements. The model exhibits a slight improvement from baseline answering complex regulatory questions (detailed QA) and expanding acronyms. This study demonstrates the potential of domain-specific LLMs in regulatory text interpretation and lays the groundwork for future research in specialized NLP evaluation methodologies.
%U https://aclanthology.org/2025.finnlp-1.39/
%P 326-334
Markdown (Informal)
[A Scalable Framework for Legal Text Understanding in Regulatory and Financial Contexts.](https://aclanthology.org/2025.finnlp-1.39/) (Martínez et al., FinNLP 2025)
ACL
- Santiago Martínez, Juan Manuel Castañeda, and Ruben Manrique. 2025. A Scalable Framework for Legal Text Understanding in Regulatory and Financial Contexts.. In Proceedings of the Joint Workshop of the 9th Financial Technology and Natural Language Processing (FinNLP), the 6th Financial Narrative Processing (FNP), and the 1st Workshop on Large Language Models for Finance and Legal (LLMFinLegal), pages 326–334, Abu Dhabi, UAE. Association for Computational Linguistics.