Hierarchical Long-Document Summarization using LED for Legal Judgments

Reshma Sheik; Noah John Puthayathu; Fathima Firose A; Jonathan Paul

Hierarchical Long-Document Summarization using LED for Legal Judgments

Reshma Sheik, Noah John Puthayathu, Fathima Firose A, Jonathan Paul

Correct Metadata for

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the PDF.)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Abstract

This paper describes our system for the L-SUMM shared task on legal document summarization. Our approach is built on the Longformer Encoder-Decoder (LED) model, which we augment with a multi-level summarization strategy tailored for legal documents that are substantially longer than typical transformer input limits. The system achieved competitive performance on the legal judgment summarization task through optimized training strategies, including gradient accumulation, Adafactor optimization, and hyperparameter tuning. Our findings indicate that combining hierarchical processing with strategically assigned global attention enables more reliable summarization of lengthy legal texts.

Anthology ID:: 2025.justnlp-main.22
Volume:: Proceedings of the 1st Workshop on NLP for Empowering Justice (JUST-NLP 2025)
Month:: December
Year:: 2025
Address:: Mumbai, India
Editors:: Ashutosh Modi, Saptarshi Ghosh, Asif Ekbal, Pawan Goyal, Sarika Jain, Abhinav Joshi, Shivani Mishra, Debtanu Datta, Shounak Paul, Kshetrimayum Boynao Singh, Sandeep Kumar
Venues:: JUSTNLP | WS
SIG:
Publisher:: Association for Computational Linguistics
Note:
Pages:: 191–195
Language:
URL:: https://aclanthology.org/2025.justnlp-main.22/
DOI:
Bibkey:
Cite (ACL):: Reshma Sheik, Noah John Puthayathu, Fathima Firose A, and Jonathan Paul. 2025. Hierarchical Long-Document Summarization using LED for Legal Judgments. In Proceedings of the 1st Workshop on NLP for Empowering Justice (JUST-NLP 2025), pages 191–195, Mumbai, India. Association for Computational Linguistics.
Cite (Informal):: Hierarchical Long-Document Summarization using LED for Legal Judgments (Sheik et al., JUSTNLP 2025)
Copy Citation:
PDF:: https://aclanthology.org/2025.justnlp-main.22.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{sheik-etal-2025-hierarchical,
    title = "Hierarchical Long-Document Summarization using {LED} for Legal Judgments",
    author = "Sheik, Reshma  and
      Puthayathu, Noah John  and
      A, Fathima Firose  and
      Paul, Jonathan",
    editor = "Modi, Ashutosh  and
      Ghosh, Saptarshi  and
      Ekbal, Asif  and
      Goyal, Pawan  and
      Jain, Sarika  and
      Joshi, Abhinav  and
      Mishra, Shivani  and
      Datta, Debtanu  and
      Paul, Shounak  and
      Singh, Kshetrimayum Boynao  and
      Kumar, Sandeep",
    booktitle = "Proceedings of the 1st Workshop on NLP for Empowering Justice (JUST-NLP 2025)",
    month = dec,
    year = "2025",
    address = "Mumbai, India",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.justnlp-main.22/",
    pages = "191--195",
    ISBN = "979-8-89176-312-8",
    abstract = "This paper describes our system for the L-SUMM shared task on legal document summarization. Our approach is built on the Longformer Encoder-Decoder (LED) model, which we augment with a multi-level summarization strategy tailored for legal documents that are substantially longer than typical transformer input limits. The system achieved competitive performance on the legal judgment summarization task through optimized training strategies, including gradient accumulation, Adafactor optimization, and hyperparameter tuning. Our findings indicate that combining hierarchical processing with strategically assigned global attention enables more reliable summarization of lengthy legal texts."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sheik-etal-2025-hierarchical">
    <titleInfo>
        <title>Hierarchical Long-Document Summarization using LED for Legal Judgments</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Reshma</namePart>
        <namePart type="family">Sheik</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Noah</namePart>
        <namePart type="given">John</namePart>
        <namePart type="family">Puthayathu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Fathima</namePart>
        <namePart type="given">Firose</namePart>
        <namePart type="family">A</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jonathan</namePart>
        <namePart type="family">Paul</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 1st Workshop on NLP for Empowering Justice (JUST-NLP 2025)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Ashutosh</namePart>
            <namePart type="family">Modi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Saptarshi</namePart>
            <namePart type="family">Ghosh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Asif</namePart>
            <namePart type="family">Ekbal</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Pawan</namePart>
            <namePart type="family">Goyal</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sarika</namePart>
            <namePart type="family">Jain</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Abhinav</namePart>
            <namePart type="family">Joshi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Shivani</namePart>
            <namePart type="family">Mishra</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Debtanu</namePart>
            <namePart type="family">Datta</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Shounak</namePart>
            <namePart type="family">Paul</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kshetrimayum</namePart>
            <namePart type="given">Boynao</namePart>
            <namePart type="family">Singh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sandeep</namePart>
            <namePart type="family">Kumar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Mumbai, India</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-312-8</identifier>
    </relatedItem>
    <abstract>This paper describes our system for the L-SUMM shared task on legal document summarization. Our approach is built on the Longformer Encoder-Decoder (LED) model, which we augment with a multi-level summarization strategy tailored for legal documents that are substantially longer than typical transformer input limits. The system achieved competitive performance on the legal judgment summarization task through optimized training strategies, including gradient accumulation, Adafactor optimization, and hyperparameter tuning. Our findings indicate that combining hierarchical processing with strategically assigned global attention enables more reliable summarization of lengthy legal texts.</abstract>
    <identifier type="citekey">sheik-etal-2025-hierarchical</identifier>
    <location>
        <url>https://aclanthology.org/2025.justnlp-main.22/</url>
    </location>
    <part>
        <date>2025-12</date>
        <extent unit="page">
            <start>191</start>
            <end>195</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T Hierarchical Long-Document Summarization using LED for Legal Judgments
%A Sheik, Reshma
%A Puthayathu, Noah John
%A A, Fathima Firose
%A Paul, Jonathan
%Y Modi, Ashutosh
%Y Ghosh, Saptarshi
%Y Ekbal, Asif
%Y Goyal, Pawan
%Y Jain, Sarika
%Y Joshi, Abhinav
%Y Mishra, Shivani
%Y Datta, Debtanu
%Y Paul, Shounak
%Y Singh, Kshetrimayum Boynao
%Y Kumar, Sandeep
%S Proceedings of the 1st Workshop on NLP for Empowering Justice (JUST-NLP 2025)
%D 2025
%8 December
%I Association for Computational Linguistics
%C Mumbai, India
%@ 979-8-89176-312-8
%F sheik-etal-2025-hierarchical
%X This paper describes our system for the L-SUMM shared task on legal document summarization. Our approach is built on the Longformer Encoder-Decoder (LED) model, which we augment with a multi-level summarization strategy tailored for legal documents that are substantially longer than typical transformer input limits. The system achieved competitive performance on the legal judgment summarization task through optimized training strategies, including gradient accumulation, Adafactor optimization, and hyperparameter tuning. Our findings indicate that combining hierarchical processing with strategically assigned global attention enables more reliable summarization of lengthy legal texts.
%U https://aclanthology.org/2025.justnlp-main.22/
%P 191-195

Download as File

Markdown (Informal)

[Hierarchical Long-Document Summarization using LED for Legal Judgments](https://aclanthology.org/2025.justnlp-main.22/) (Sheik et al., JUSTNLP 2025)

Hierarchical Long-Document Summarization using LED for Legal Judgments (Sheik et al., JUSTNLP 2025)

ACL

Reshma Sheik, Noah John Puthayathu, Fathima Firose A, and Jonathan Paul. 2025. Hierarchical Long-Document Summarization using LED for Legal Judgments. In Proceedings of the 1st Workshop on NLP for Empowering Justice (JUST-NLP 2025), pages 191–195, Mumbai, India. Association for Computational Linguistics.