@inproceedings{noce-etal-2026-jurifindit,
title = "{J}uri{F}ind{IT}: an {I}talian legal retrieval dataset",
author = "Noce, Niko Dalla and
Colla, Davide and
Doust, Sina Farhang and
De Mattei, Lorenzo and
Bacciu, Davide",
editor = "Demberg, Vera and
Inui, Kentaro and
Marquez, Llu{\'i}s",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EACL} 2026",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-eacl.221/",
pages = "4223--4241",
ISBN = "979-8-89176-386-9",
abstract = "Statutory article retrieval (SAR) targets retrieval of legislative provisions relevant to a natural language question. The lexical gap between everyday queries and specialized legal language, as well as the structural dependencies of statute law, makes it a challenging task. Here, we introduce JuriFindIT, the first SAR dataset for the Italian legal domain and the first to explicitly encode cross-article references extracted from national legal code. The dataset covers four macro-areas{---}civil law, criminal law, anti-money laundering and counter-terrorism, and privacy{---}and includes 895 expert-authored questions and 169,301 generated ones, linked to more than 23,000 statutory articles. We provide retrieval models fine-tuned on JuriFindIT, proposing a pipeline that integrates dense encoders with an heterogeneous legislative graph, achieving consistent improvements over prior SAR approaches."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="noce-etal-2026-jurifindit">
<titleInfo>
<title>JuriFindIT: an Italian legal retrieval dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Niko</namePart>
<namePart type="given">Dalla</namePart>
<namePart type="family">Noce</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Davide</namePart>
<namePart type="family">Colla</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sina</namePart>
<namePart type="given">Farhang</namePart>
<namePart type="family">Doust</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lorenzo</namePart>
<namePart type="family">De Mattei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Davide</namePart>
<namePart type="family">Bacciu</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>Findings of the Association for Computational Linguistics: EACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Marquez</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">979-8-89176-386-9</identifier>
</relatedItem>
<abstract>Statutory article retrieval (SAR) targets retrieval of legislative provisions relevant to a natural language question. The lexical gap between everyday queries and specialized legal language, as well as the structural dependencies of statute law, makes it a challenging task. Here, we introduce JuriFindIT, the first SAR dataset for the Italian legal domain and the first to explicitly encode cross-article references extracted from national legal code. The dataset covers four macro-areas—civil law, criminal law, anti-money laundering and counter-terrorism, and privacy—and includes 895 expert-authored questions and 169,301 generated ones, linked to more than 23,000 statutory articles. We provide retrieval models fine-tuned on JuriFindIT, proposing a pipeline that integrates dense encoders with an heterogeneous legislative graph, achieving consistent improvements over prior SAR approaches.</abstract>
<identifier type="citekey">noce-etal-2026-jurifindit</identifier>
<location>
<url>https://aclanthology.org/2026.findings-eacl.221/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>4223</start>
<end>4241</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T JuriFindIT: an Italian legal retrieval dataset
%A Noce, Niko Dalla
%A Colla, Davide
%A Doust, Sina Farhang
%A De Mattei, Lorenzo
%A Bacciu, Davide
%Y Demberg, Vera
%Y Inui, Kentaro
%Y Marquez, Lluís
%S Findings of the Association for Computational Linguistics: EACL 2026
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-386-9
%F noce-etal-2026-jurifindit
%X Statutory article retrieval (SAR) targets retrieval of legislative provisions relevant to a natural language question. The lexical gap between everyday queries and specialized legal language, as well as the structural dependencies of statute law, makes it a challenging task. Here, we introduce JuriFindIT, the first SAR dataset for the Italian legal domain and the first to explicitly encode cross-article references extracted from national legal code. The dataset covers four macro-areas—civil law, criminal law, anti-money laundering and counter-terrorism, and privacy—and includes 895 expert-authored questions and 169,301 generated ones, linked to more than 23,000 statutory articles. We provide retrieval models fine-tuned on JuriFindIT, proposing a pipeline that integrates dense encoders with an heterogeneous legislative graph, achieving consistent improvements over prior SAR approaches.
%U https://aclanthology.org/2026.findings-eacl.221/
%P 4223-4241
Markdown (Informal)
[JuriFindIT: an Italian legal retrieval dataset](https://aclanthology.org/2026.findings-eacl.221/) (Noce et al., Findings 2026)
ACL
- Niko Dalla Noce, Davide Colla, Sina Farhang Doust, Lorenzo De Mattei, and Davide Bacciu. 2026. JuriFindIT: an Italian legal retrieval dataset. In Findings of the Association for Computational Linguistics: EACL 2026, pages 4223–4241, Rabat, Morocco. Association for Computational Linguistics.