@inproceedings{rajaraman-veeramani-2024-semantists,
title = "Semantists at {L}egal{L}ens-2024: Data-efficient Training of {LLM}{'}s for Legal Violation Identification",
author = "Rajaraman, Kanagasabai and
Veeramani, Hariram",
editor = "Aletras, Nikolaos and
Chalkidis, Ilias and
Barrett, Leslie and
Goan{\textcommabelow{t}}{\u{a}}, C{\u{a}}t{\u{a}}lina and
Preo{\textcommabelow{t}}iuc-Pietro, Daniel and
Spanakis, Gerasimos",
booktitle = "Proceedings of the Natural Legal Language Processing Workshop 2024",
month = nov,
year = "2024",
address = "Miami, FL, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.nllp-1.31",
pages = "355--360",
abstract = "In this paper, we describe our system for LegalLens-2024 Shared Task on automatically identifying legal violations from unstructured text sources. We participate in Subtask B, called Legal Natural Language Inference (L-NLI), that aims to predict the relationship between a given premise summarizing a class action complaint and a hypothesis from an online media text, indicating any association between the review and the complaint. This task is challenging as it provides only limited labelled data. In our work, we adopt LLM based methods and explore various data-efficient learning approaches for maximizing performance. In the end, our best model employed an ensemble of LLM{'}s fine-tuned on the task-specific data, and achieved a Macro F1 score of 78.5{\%} on test data, and ranked 2nd among all teams submissions.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rajaraman-veeramani-2024-semantists">
<titleInfo>
<title>Semantists at LegalLens-2024: Data-efficient Training of LLM’s for Legal Violation Identification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kanagasabai</namePart>
<namePart type="family">Rajaraman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hariram</namePart>
<namePart type="family">Veeramani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Natural Legal Language Processing Workshop 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikolaos</namePart>
<namePart type="family">Aletras</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ilias</namePart>
<namePart type="family">Chalkidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leslie</namePart>
<namePart type="family">Barrett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cătălina</namePart>
<namePart type="family">Goan\textcommabelowtă</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Preo\textcommabelowtiuc-Pietro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gerasimos</namePart>
<namePart type="family">Spanakis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, FL, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we describe our system for LegalLens-2024 Shared Task on automatically identifying legal violations from unstructured text sources. We participate in Subtask B, called Legal Natural Language Inference (L-NLI), that aims to predict the relationship between a given premise summarizing a class action complaint and a hypothesis from an online media text, indicating any association between the review and the complaint. This task is challenging as it provides only limited labelled data. In our work, we adopt LLM based methods and explore various data-efficient learning approaches for maximizing performance. In the end, our best model employed an ensemble of LLM’s fine-tuned on the task-specific data, and achieved a Macro F1 score of 78.5% on test data, and ranked 2nd among all teams submissions.</abstract>
<identifier type="citekey">rajaraman-veeramani-2024-semantists</identifier>
<location>
<url>https://aclanthology.org/2024.nllp-1.31</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>355</start>
<end>360</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Semantists at LegalLens-2024: Data-efficient Training of LLM’s for Legal Violation Identification
%A Rajaraman, Kanagasabai
%A Veeramani, Hariram
%Y Aletras, Nikolaos
%Y Chalkidis, Ilias
%Y Barrett, Leslie
%Y Goan\textcommabelowtă, Cătălina
%Y Preo\textcommabelowtiuc-Pietro, Daniel
%Y Spanakis, Gerasimos
%S Proceedings of the Natural Legal Language Processing Workshop 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, FL, USA
%F rajaraman-veeramani-2024-semantists
%X In this paper, we describe our system for LegalLens-2024 Shared Task on automatically identifying legal violations from unstructured text sources. We participate in Subtask B, called Legal Natural Language Inference (L-NLI), that aims to predict the relationship between a given premise summarizing a class action complaint and a hypothesis from an online media text, indicating any association between the review and the complaint. This task is challenging as it provides only limited labelled data. In our work, we adopt LLM based methods and explore various data-efficient learning approaches for maximizing performance. In the end, our best model employed an ensemble of LLM’s fine-tuned on the task-specific data, and achieved a Macro F1 score of 78.5% on test data, and ranked 2nd among all teams submissions.
%U https://aclanthology.org/2024.nllp-1.31
%P 355-360
Markdown (Informal)
[Semantists at LegalLens-2024: Data-efficient Training of LLM’s for Legal Violation Identification](https://aclanthology.org/2024.nllp-1.31) (Rajaraman & Veeramani, NLLP 2024)
ACL