@inproceedings{chowdhury-etal-2024-cross,
title = "Cross Examine: An Ensemble-based approach to leverage Large Language Models for Legal Text Analytics",
author = "Chowdhury, Saurav and
Dey, Lipika and
Joshi, Suyog",
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-1.16",
pages = "194--204",
abstract = "Legal documents are complex in nature, describing a course of argumentative reasoning that is followed to settle a case. Churning through large volumes of legal documents is a daily requirement for a large number of professionals who need access to the information embedded in them. Natural language processing methods that help in document summarization with key information components, insight extraction and question answering play a crucial role in legal text processing. Most of the existing document analysis systems use supervised machine learning, which require large volumes of annotated training data for every different application and are expensive to build. In this paper we propose a legal text analytics pipeline using Large Language Models (LLM), which can work with little or no training data. For document summarization, we propose an iterative pipeline using retrieval augmented generation to ensure that the generated text remains contextually relevant. For question answering, we propose a novel ontology-driven ensemble approach similar to cross-examination that exploits questioning and verification principles. A knowledge graph, created with the extracted information, stores the key entities and relationships reflecting the repository content structure. A new dataset is created with Indian court documents related to bail applications for cases filed under Protection of Children from Sexual Offences (POCSO) Act, 2012 an Indian law to protect children from sexual abuse and offences. Analysis of insights extracted from the answers reveal patterns of crime and social conditions leading to those crimes, which are important inputs for social scientists as well as legal system.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chowdhury-etal-2024-cross">
<titleInfo>
<title>Cross Examine: An Ensemble-based approach to leverage Large Language Models for Legal Text Analytics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saurav</namePart>
<namePart type="family">Chowdhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lipika</namePart>
<namePart type="family">Dey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Suyog</namePart>
<namePart type="family">Joshi</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>Legal documents are complex in nature, describing a course of argumentative reasoning that is followed to settle a case. Churning through large volumes of legal documents is a daily requirement for a large number of professionals who need access to the information embedded in them. Natural language processing methods that help in document summarization with key information components, insight extraction and question answering play a crucial role in legal text processing. Most of the existing document analysis systems use supervised machine learning, which require large volumes of annotated training data for every different application and are expensive to build. In this paper we propose a legal text analytics pipeline using Large Language Models (LLM), which can work with little or no training data. For document summarization, we propose an iterative pipeline using retrieval augmented generation to ensure that the generated text remains contextually relevant. For question answering, we propose a novel ontology-driven ensemble approach similar to cross-examination that exploits questioning and verification principles. A knowledge graph, created with the extracted information, stores the key entities and relationships reflecting the repository content structure. A new dataset is created with Indian court documents related to bail applications for cases filed under Protection of Children from Sexual Offences (POCSO) Act, 2012 an Indian law to protect children from sexual abuse and offences. Analysis of insights extracted from the answers reveal patterns of crime and social conditions leading to those crimes, which are important inputs for social scientists as well as legal system.</abstract>
<identifier type="citekey">chowdhury-etal-2024-cross</identifier>
<location>
<url>https://aclanthology.org/2024.nllp-1.16</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>194</start>
<end>204</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cross Examine: An Ensemble-based approach to leverage Large Language Models for Legal Text Analytics
%A Chowdhury, Saurav
%A Dey, Lipika
%A Joshi, Suyog
%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 chowdhury-etal-2024-cross
%X Legal documents are complex in nature, describing a course of argumentative reasoning that is followed to settle a case. Churning through large volumes of legal documents is a daily requirement for a large number of professionals who need access to the information embedded in them. Natural language processing methods that help in document summarization with key information components, insight extraction and question answering play a crucial role in legal text processing. Most of the existing document analysis systems use supervised machine learning, which require large volumes of annotated training data for every different application and are expensive to build. In this paper we propose a legal text analytics pipeline using Large Language Models (LLM), which can work with little or no training data. For document summarization, we propose an iterative pipeline using retrieval augmented generation to ensure that the generated text remains contextually relevant. For question answering, we propose a novel ontology-driven ensemble approach similar to cross-examination that exploits questioning and verification principles. A knowledge graph, created with the extracted information, stores the key entities and relationships reflecting the repository content structure. A new dataset is created with Indian court documents related to bail applications for cases filed under Protection of Children from Sexual Offences (POCSO) Act, 2012 an Indian law to protect children from sexual abuse and offences. Analysis of insights extracted from the answers reveal patterns of crime and social conditions leading to those crimes, which are important inputs for social scientists as well as legal system.
%U https://aclanthology.org/2024.nllp-1.16
%P 194-204
Markdown (Informal)
[Cross Examine: An Ensemble-based approach to leverage Large Language Models for Legal Text Analytics](https://aclanthology.org/2024.nllp-1.16) (Chowdhury et al., NLLP 2024)
ACL