@inproceedings{lee-etal-2026-kolegalqa,
title = "{K}o{L}egal{QA}: A {K}orean Legal {QA} Dataset for Trustworthy and Explanation-Grounded Legal {AI}",
author = "Lee, Yongtae and
Lee, Surin and
Kim, Sumin and
Rahman, S M Wahidur and
Lee, Heung-No",
editor = "Chang, Kai-Wei and
Mehrabi, Ninareh and
Krishna, Satyapriya and
Das, Anubrata and
Dhamala, Jwala and
Cao, Yang Trista and
Kumarage, Tharindu and
Ramakrishna, Anil and
Christodoulopoulos, Christos and
Wan, Yixin and
Galystan, Aram and
Kumar, Anoop and
Gupta, Rahul",
booktitle = "Proceedings of the 6th Workshop on Trustworthy {NLP} ({T}rust{NLP} 2026)",
month = jul,
year = "2026",
address = "San Diego, California",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.trustnlp-main.13/",
pages = "240--255",
ISBN = "979-8-89176-418-7",
abstract = "Legal QA systems may benefit from training data that is expert-verified and associated with statutory provisions, as fluent generation alone cannot guarantee legally relevant and citation-supported outputs. However, existing Korean legal datasets provide limited support for legal QA and statute-associated response generation. To address this gap, we introduce KoLegalQA, a large-scale Korean legal question{--}answer corpus designed for research on legal QA and explanation-oriented legal response generation in real-world consultation scenarios. The dataset comprises 19k consultations collected from government-operated services, with all responses originally authored or verified by licensed legal professionals. Unlike prior resources, KoLegalQA provides explicit statutory references and clause-level summaries, enabling research on citation-associated and explanation-oriented legal response generation. We benchmark six Korean-capable LLMs using both automated evaluation (G-Eval) and human assessment across multiple criteria, including legal correctness, reasoning quality, and citation relevance. Experimental results show that fine-tuning on KoLegalQA generally improves legal reasoning validity and statute-associated response generation across most evaluated models. We present this resource as a practical benchmark dataset for Korean legal NLP research. Dataset splits, preprocessing scripts, and evaluation code will be publicly released to support reproducible research."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lee-etal-2026-kolegalqa">
<titleInfo>
<title>KoLegalQA: A Korean Legal QA Dataset for Trustworthy and Explanation-Grounded Legal AI</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yongtae</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Surin</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sumin</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">S</namePart>
<namePart type="given">M</namePart>
<namePart type="given">Wahidur</namePart>
<namePart type="family">Rahman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heung-No</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 6th Workshop on Trustworthy NLP (TrustNLP 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kai-Wei</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ninareh</namePart>
<namePart type="family">Mehrabi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Satyapriya</namePart>
<namePart type="family">Krishna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anubrata</namePart>
<namePart type="family">Das</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jwala</namePart>
<namePart type="family">Dhamala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="given">Trista</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tharindu</namePart>
<namePart type="family">Kumarage</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anil</namePart>
<namePart type="family">Ramakrishna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yixin</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aram</namePart>
<namePart type="family">Galystan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anoop</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rahul</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-418-7</identifier>
</relatedItem>
<abstract>Legal QA systems may benefit from training data that is expert-verified and associated with statutory provisions, as fluent generation alone cannot guarantee legally relevant and citation-supported outputs. However, existing Korean legal datasets provide limited support for legal QA and statute-associated response generation. To address this gap, we introduce KoLegalQA, a large-scale Korean legal question–answer corpus designed for research on legal QA and explanation-oriented legal response generation in real-world consultation scenarios. The dataset comprises 19k consultations collected from government-operated services, with all responses originally authored or verified by licensed legal professionals. Unlike prior resources, KoLegalQA provides explicit statutory references and clause-level summaries, enabling research on citation-associated and explanation-oriented legal response generation. We benchmark six Korean-capable LLMs using both automated evaluation (G-Eval) and human assessment across multiple criteria, including legal correctness, reasoning quality, and citation relevance. Experimental results show that fine-tuning on KoLegalQA generally improves legal reasoning validity and statute-associated response generation across most evaluated models. We present this resource as a practical benchmark dataset for Korean legal NLP research. Dataset splits, preprocessing scripts, and evaluation code will be publicly released to support reproducible research.</abstract>
<identifier type="citekey">lee-etal-2026-kolegalqa</identifier>
<location>
<url>https://aclanthology.org/2026.trustnlp-main.13/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>240</start>
<end>255</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T KoLegalQA: A Korean Legal QA Dataset for Trustworthy and Explanation-Grounded Legal AI
%A Lee, Yongtae
%A Lee, Surin
%A Kim, Sumin
%A Rahman, S. M. Wahidur
%A Lee, Heung-No
%Y Chang, Kai-Wei
%Y Mehrabi, Ninareh
%Y Krishna, Satyapriya
%Y Das, Anubrata
%Y Dhamala, Jwala
%Y Cao, Yang Trista
%Y Kumarage, Tharindu
%Y Ramakrishna, Anil
%Y Christodoulopoulos, Christos
%Y Wan, Yixin
%Y Galystan, Aram
%Y Kumar, Anoop
%Y Gupta, Rahul
%S Proceedings of the 6th Workshop on Trustworthy NLP (TrustNLP 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California
%@ 979-8-89176-418-7
%F lee-etal-2026-kolegalqa
%X Legal QA systems may benefit from training data that is expert-verified and associated with statutory provisions, as fluent generation alone cannot guarantee legally relevant and citation-supported outputs. However, existing Korean legal datasets provide limited support for legal QA and statute-associated response generation. To address this gap, we introduce KoLegalQA, a large-scale Korean legal question–answer corpus designed for research on legal QA and explanation-oriented legal response generation in real-world consultation scenarios. The dataset comprises 19k consultations collected from government-operated services, with all responses originally authored or verified by licensed legal professionals. Unlike prior resources, KoLegalQA provides explicit statutory references and clause-level summaries, enabling research on citation-associated and explanation-oriented legal response generation. We benchmark six Korean-capable LLMs using both automated evaluation (G-Eval) and human assessment across multiple criteria, including legal correctness, reasoning quality, and citation relevance. Experimental results show that fine-tuning on KoLegalQA generally improves legal reasoning validity and statute-associated response generation across most evaluated models. We present this resource as a practical benchmark dataset for Korean legal NLP research. Dataset splits, preprocessing scripts, and evaluation code will be publicly released to support reproducible research.
%U https://aclanthology.org/2026.trustnlp-main.13/
%P 240-255
Markdown (Informal)
[KoLegalQA: A Korean Legal QA Dataset for Trustworthy and Explanation-Grounded Legal AI](https://aclanthology.org/2026.trustnlp-main.13/) (Lee et al., TrustNLP 2026)
ACL