<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="noce-etal-2026-justifit">
    <titleInfo>
        <title>JustifIT-QA: Evidence-Grounded Legal Question Answering in Italian</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">Bacciu</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>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-459-0</identifier>
    </relatedItem>
    <abstract>Grounded legal question answering requires retrieving the relevant statutory provisions, generating legally sound answers, and supporting them with explicit evidence. We introduce JustifIT-QA, the first Italian statutory QA dataset with expert-written answers and fine-grained evidence spans, and present DARv2, a dense retriever that improves coverage of relevant legal texts. Building on this retrieval layer, we study a judge-based feedback loop in which an LLM critiques and refines generated answers, and we evaluate LLMs as judges for legal answer correctness. Results show that feedback improves expert-rated answer quality when relevant context is retrieved, while evidence extraction benefits from stronger models but remains challenging. We release the dataset, code, and retriever to support future research on grounded and explainable legal QA in Italian.</abstract>
    <identifier type="citekey">noce-etal-2026-justifit</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.593/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>13661</start>
            <end>13685</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T JustifIT-QA: Evidence-Grounded Legal Question Answering in Italian
%A Noce, Niko Dalla
%A Bacciu, Davide
%A Doust, Sina Farhang
%A De Mattei, Lorenzo
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F noce-etal-2026-justifit
%X Grounded legal question answering requires retrieving the relevant statutory provisions, generating legally sound answers, and supporting them with explicit evidence. We introduce JustifIT-QA, the first Italian statutory QA dataset with expert-written answers and fine-grained evidence spans, and present DARv2, a dense retriever that improves coverage of relevant legal texts. Building on this retrieval layer, we study a judge-based feedback loop in which an LLM critiques and refines generated answers, and we evaluate LLMs as judges for legal answer correctness. Results show that feedback improves expert-rated answer quality when relevant context is retrieved, while evidence extraction benefits from stronger models but remains challenging. We release the dataset, code, and retriever to support future research on grounded and explainable legal QA in Italian.
%U https://aclanthology.org/2026.emnlp-main.593/
%P 13661-13685

Markdown (Informal)

[JustifIT-QA: Evidence-Grounded Legal Question Answering in Italian](https://aclanthology.org/2026.emnlp-main.593/) (Noce et al., EMNLP 2026)

• JustifIT-QA: Evidence-Grounded Legal Question Answering in Italian (Noce et al., EMNLP 2026)

ACL

• Niko Dalla Noce, Davide Bacciu, Sina Farhang Doust, and Lorenzo De Mattei. 2026. JustifIT-QA: Evidence-Grounded Legal Question Answering in Italian. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 13661–13685, Budapest, Hungary. Association for Computational Linguistics.