<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="prior-etal-2025-risks">
    <titleInfo>
        <title>Risks and Limits of Automatic Consolidation of Statutes</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Max</namePart>
        <namePart type="family">Prior</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Adrian</namePart>
        <namePart type="family">Hof</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Niklas</namePart>
        <namePart type="family">Wais</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Matthias</namePart>
        <namePart type="family">Grabmair</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Natural Legal Language Processing Workshop 2025</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Nikolaos</namePart>
            <namePart type="family">Aletras</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ilias</namePart>
            <namePart type="family">Chalkidis</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Leslie</namePart>
            <namePart type="family">Barrett</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Cătălina</namePart>
            <namePart type="family">Goanță</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Daniel</namePart>
            <namePart type="family">Preoțiuc-Pietro</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Gerasimos</namePart>
            <namePart type="family">Spanakis</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Suzhou, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-338-8</identifier>
    </relatedItem>
    <abstract>As in many countries of the Civil Law tradition, consolidated versions of statutes - statutes with added amendments - are difficult to obtain reliably and promptly in Germany. This gap has prompted interest in using large language models (LLMs) to ‘synthesize’ current and historical versions from amendments. Our paper experiments with an LLM-based consolidation framework and a dataset of 908 amendment–law pairs drawn from 140 Federal Law Gazette documents across four major codes. While automated metrics show high textual similarity (93-99%) for single-step and multi-step amendment chains, only 50.3% of exact matches (single-step) and 20.51% (multi-step) could be achieved; our expert assessment reveals that non-trivial errors persist and that even small divergences can carry legal significance. We therefore argue that any public or private deployment must treat outputs as drafts subject to rigorous human verification.</abstract>
    <identifier type="citekey">prior-etal-2025-risks</identifier>
    <location>
        <url>https://aclanthology.org/2025.nllp-1.29/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>396</start>
            <end>407</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Risks and Limits of Automatic Consolidation of Statutes
%A Prior, Max
%A Hof, Adrian
%A Wais, Niklas
%A Grabmair, Matthias
%Y Aletras, Nikolaos
%Y Chalkidis, Ilias
%Y Barrett, Leslie
%Y Goanță, Cătălina
%Y Preoțiuc-Pietro, Daniel
%Y Spanakis, Gerasimos
%S Proceedings of the Natural Legal Language Processing Workshop 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-338-8
%F prior-etal-2025-risks
%X As in many countries of the Civil Law tradition, consolidated versions of statutes - statutes with added amendments - are difficult to obtain reliably and promptly in Germany. This gap has prompted interest in using large language models (LLMs) to ‘synthesize’ current and historical versions from amendments. Our paper experiments with an LLM-based consolidation framework and a dataset of 908 amendment–law pairs drawn from 140 Federal Law Gazette documents across four major codes. While automated metrics show high textual similarity (93-99%) for single-step and multi-step amendment chains, only 50.3% of exact matches (single-step) and 20.51% (multi-step) could be achieved; our expert assessment reveals that non-trivial errors persist and that even small divergences can carry legal significance. We therefore argue that any public or private deployment must treat outputs as drafts subject to rigorous human verification.
%U https://aclanthology.org/2025.nllp-1.29/
%P 396-407

Markdown (Informal)

[Risks and Limits of Automatic Consolidation of Statutes](https://aclanthology.org/2025.nllp-1.29/) (Prior et al., NLLP 2025)

• Risks and Limits of Automatic Consolidation of Statutes (Prior et al., NLLP 2025)

ACL

• Max Prior, Adrian Hof, Niklas Wais, and Matthias Grabmair. 2025. Risks and Limits of Automatic Consolidation of Statutes. In Proceedings of the Natural Legal Language Processing Workshop 2025, pages 396–407, Suzhou, China. Association for Computational Linguistics.