@inproceedings{kulkarni-etal-2026-long,
title = "Long-Context Long-Form Question Answering for Legal Domain",
author = "Kulkarni, Anagha and
Jhaveri, Parin Rajesh and
Shrestha, Prasha and
Han, Yu Tong and
Amini, Reza and
Madahian, Behrouz",
editor = {Matusevych, Yevgen and
Eryi{\u{g}}it, G{\"u}l{\c{s}}en and
Aletras, Nikolaos},
booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 5: Industry Track)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.eacl-industry.54/",
pages = "728--751",
ISBN = "979-8-89176-384-5",
abstract = "Legal documents have complex document layouts involving multiple nested sections, lengthy footnotes and further use specialized linguistic devices like intricate syntax and domain-specific vocabulary to ensure precision and authority. These inherent characteristics of legal documents make question answering challenging, and particularly so when the answer to the question spans several pages (i.e. requires long-context) and is required to be comprehensive (i.e. a long-form answer).In this paper, we address the challenges of long-context question answering in context of long-form answers given the idiosyncrasies of legal documents. We propose a question answering system that can (a) deconstruct domain-specific vocabulary for better retrieval from source documents, (b) parse complex document layouts while isolating sections and footnotes and linking them appropriately, (c) generate comprehensive answers using precise domain-specific vocabulary. We also introduce a coverage metric that classifies the performance into recall-based coverage categories allowing human users to evaluate the recall with ease. By leveraging the expertise of professionals from fields such as law and corporate tax, we curate a QA dataset. Through comprehensive experiments and ablation studies, we demonstrate the usability and merit of the proposed system."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kulkarni-etal-2026-long">
<titleInfo>
<title>Long-Context Long-Form Question Answering for Legal Domain</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anagha</namePart>
<namePart type="family">Kulkarni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Parin</namePart>
<namePart type="given">Rajesh</namePart>
<namePart type="family">Jhaveri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Prasha</namePart>
<namePart type="family">Shrestha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="given">Tong</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reza</namePart>
<namePart type="family">Amini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Behrouz</namePart>
<namePart type="family">Madahian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 5: Industry Track)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yevgen</namePart>
<namePart type="family">Matusevych</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gülşen</namePart>
<namePart type="family">Eryiğit</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikolaos</namePart>
<namePart type="family">Aletras</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-384-5</identifier>
</relatedItem>
<abstract>Legal documents have complex document layouts involving multiple nested sections, lengthy footnotes and further use specialized linguistic devices like intricate syntax and domain-specific vocabulary to ensure precision and authority. These inherent characteristics of legal documents make question answering challenging, and particularly so when the answer to the question spans several pages (i.e. requires long-context) and is required to be comprehensive (i.e. a long-form answer).In this paper, we address the challenges of long-context question answering in context of long-form answers given the idiosyncrasies of legal documents. We propose a question answering system that can (a) deconstruct domain-specific vocabulary for better retrieval from source documents, (b) parse complex document layouts while isolating sections and footnotes and linking them appropriately, (c) generate comprehensive answers using precise domain-specific vocabulary. We also introduce a coverage metric that classifies the performance into recall-based coverage categories allowing human users to evaluate the recall with ease. By leveraging the expertise of professionals from fields such as law and corporate tax, we curate a QA dataset. Through comprehensive experiments and ablation studies, we demonstrate the usability and merit of the proposed system.</abstract>
<identifier type="citekey">kulkarni-etal-2026-long</identifier>
<location>
<url>https://aclanthology.org/2026.eacl-industry.54/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>728</start>
<end>751</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Long-Context Long-Form Question Answering for Legal Domain
%A Kulkarni, Anagha
%A Jhaveri, Parin Rajesh
%A Shrestha, Prasha
%A Han, Yu Tong
%A Amini, Reza
%A Madahian, Behrouz
%Y Matusevych, Yevgen
%Y Eryiğit, Gülşen
%Y Aletras, Nikolaos
%S Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 5: Industry Track)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-384-5
%F kulkarni-etal-2026-long
%X Legal documents have complex document layouts involving multiple nested sections, lengthy footnotes and further use specialized linguistic devices like intricate syntax and domain-specific vocabulary to ensure precision and authority. These inherent characteristics of legal documents make question answering challenging, and particularly so when the answer to the question spans several pages (i.e. requires long-context) and is required to be comprehensive (i.e. a long-form answer).In this paper, we address the challenges of long-context question answering in context of long-form answers given the idiosyncrasies of legal documents. We propose a question answering system that can (a) deconstruct domain-specific vocabulary for better retrieval from source documents, (b) parse complex document layouts while isolating sections and footnotes and linking them appropriately, (c) generate comprehensive answers using precise domain-specific vocabulary. We also introduce a coverage metric that classifies the performance into recall-based coverage categories allowing human users to evaluate the recall with ease. By leveraging the expertise of professionals from fields such as law and corporate tax, we curate a QA dataset. Through comprehensive experiments and ablation studies, we demonstrate the usability and merit of the proposed system.
%U https://aclanthology.org/2026.eacl-industry.54/
%P 728-751
Markdown (Informal)
[Long-Context Long-Form Question Answering for Legal Domain](https://aclanthology.org/2026.eacl-industry.54/) (Kulkarni et al., EACL 2026)
ACL
- Anagha Kulkarni, Parin Rajesh Jhaveri, Prasha Shrestha, Yu Tong Han, Reza Amini, and Behrouz Madahian. 2026. Long-Context Long-Form Question Answering for Legal Domain. In Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 5: Industry Track), pages 728–751, Rabat, Morocco. Association for Computational Linguistics.