<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Archiving and Interchange DTD v1.0 20120330//EN" "JATS-archivearticle1.dtd">
<article xmlns:xlink="http://www.w3.org/1999/xlink">
  <front>
    <journal-meta>
      <issn pub-type="ppub">1613-0073</issn>
    </journal-meta>
    <article-meta>
      <title-group>
        <article-title>AMELIA - Argument Mining Evaluation on Legal documents in ItAlian: A CALAMITA Challenge</article-title>
      </title-group>
      <contrib-group>
        <contrib contrib-type="author">
          <string-name>Giulia Grundler</string-name>
          <email>giulia.grundler2@unibo.it</email>
          <xref ref-type="aff" rid="aff0">0</xref>
          <xref ref-type="aff" rid="aff1">1</xref>
          <xref ref-type="aff" rid="aff4">4</xref>
        </contrib>
        <contrib contrib-type="author">
          <string-name>Andrea Galassi</string-name>
          <email>a.galassi@unibo.it</email>
          <xref ref-type="aff" rid="aff1">1</xref>
          <xref ref-type="aff" rid="aff2">2</xref>
          <xref ref-type="aff" rid="aff4">4</xref>
        </contrib>
        <contrib contrib-type="author">
          <string-name>Piera Santin</string-name>
          <xref ref-type="aff" rid="aff1">1</xref>
          <xref ref-type="aff" rid="aff3">3</xref>
          <xref ref-type="aff" rid="aff4">4</xref>
        </contrib>
        <contrib contrib-type="author">
          <string-name>Alessia Fidelangeli</string-name>
          <xref ref-type="aff" rid="aff0">0</xref>
          <xref ref-type="aff" rid="aff1">1</xref>
          <xref ref-type="aff" rid="aff4">4</xref>
        </contrib>
        <contrib contrib-type="author">
          <string-name>Federico Galli</string-name>
          <xref ref-type="aff" rid="aff0">0</xref>
          <xref ref-type="aff" rid="aff1">1</xref>
          <xref ref-type="aff" rid="aff4">4</xref>
        </contrib>
        <contrib contrib-type="author">
          <string-name>Elena Palmieri</string-name>
          <xref ref-type="aff" rid="aff1">1</xref>
          <xref ref-type="aff" rid="aff2">2</xref>
          <xref ref-type="aff" rid="aff4">4</xref>
        </contrib>
        <contrib contrib-type="author">
          <string-name>Francesca Lagioia</string-name>
          <xref ref-type="aff" rid="aff0">0</xref>
          <xref ref-type="aff" rid="aff1">1</xref>
          <xref ref-type="aff" rid="aff3">3</xref>
          <xref ref-type="aff" rid="aff4">4</xref>
        </contrib>
        <contrib contrib-type="author">
          <string-name>Giovanni Sartor</string-name>
          <xref ref-type="aff" rid="aff0">0</xref>
          <xref ref-type="aff" rid="aff1">1</xref>
          <xref ref-type="aff" rid="aff3">3</xref>
          <xref ref-type="aff" rid="aff4">4</xref>
        </contrib>
        <contrib contrib-type="author">
          <string-name>Paolo Torroni</string-name>
          <xref ref-type="aff" rid="aff1">1</xref>
          <xref ref-type="aff" rid="aff2">2</xref>
          <xref ref-type="aff" rid="aff4">4</xref>
        </contrib>
        <aff id="aff0">
          <label>0</label>
          <institution>CIRSFID Alma-AI, Faculty of Law, University of Bologna</institution>
          ,
          <country country="IT">Italy</country>
        </aff>
        <aff id="aff1">
          <label>1</label>
          <institution>CLiC-it 2024: Tenth Italian Conference on Computational Linguistics</institution>
        </aff>
        <aff id="aff2">
          <label>2</label>
          <institution>DISI, Alma-AI, University of Bologna</institution>
          ,
          <country country="IT">Italy</country>
        </aff>
        <aff id="aff3">
          <label>3</label>
          <institution>European University Institute, Law Department</institution>
          ,
          <country country="IT">Italy</country>
        </aff>
        <aff id="aff4">
          <label>4</label>
          <institution>LLM</institution>
          ,
          <addr-line>Argument Mining, Legal Analytics, VAT, CALAMITA, CLiC-it</addr-line>
        </aff>
      </contrib-group>
      <abstract>
        <p>This challenge consists of three classification tasks, in the context of argument mining in the legal domain. The tasks are based on a dataset of 225 Italian decisions on Value Added Tax, annotated to identify and categorize argumentative text. The objective of the first task is to classify each argumentative component as premise or conclusion, while the second and third tasks aim at classifying the type of premise: legal vs factual, and its corresponding argumentation scheme. The classes are highly unbalanced, hence evaluation is based on the macro F1 score.</p>
      </abstract>
    </article-meta>
  </front>
  <body>
    <sec id="sec-1">
      <title>-</title>
      <p>CEUR
ceur-ws.org</p>
    </sec>
    <sec id="sec-2">
      <title>1. Challenge: Introduction and Motivation</title>
      <p>
        pable of reasoning, as opposed to simply recognizing
patterns from vast amounts of data is an open research
question and the subject of a lively ongoing debate [
        <xref ref-type="bibr" rid="ref1">1</xref>
        ]. A
way to describe human reasoning is through its ability to
understand, evaluate, and invent arguments composed
by claims, evidence, and conclusions meaningfully
connected with one another [
        <xref ref-type="bibr" rid="ref2">2</xref>
        ]. For this reason, the ability
to recognize arguments could be considered as a first
step in a sequence of reasoning tasks of increasing
complexity, that goes from the detection and classification of
argumentative discourse units or argument components,
through argument structure prediction, reconstruction,
evaluation, down to argument generation. Automatizing
these tasks is the object of argument mining [
        <xref ref-type="bibr" rid="ref3 ref4">3, 4, 5</xref>
        ]. We
believe that gauging the ability of LLMs to address even
basic argument mining tasks would provide meaningful
cues as to these models’ ability to process and understand
logical relations expressed in natural language.
      </p>
      <p>While several datasets for argument mining in English
(A. Galassi)</p>
      <p>0000-0002-7255-9343 (G. Grundler); 0000-0001-9711-7042
(A. Galassi); 0000-0002-0734-9657 (P. Santin); 0000-0003-3739-5387
(F. Galli); 0000-0001-5176-8843 (E. Palmieri); 0000-0001-7083-3487
(F. Lagioia); 0000-0003-2210-0398 (G. Sartor); 0000-0002-9253-8638
(P. Torroni)
© 2024 Copyright for this paper by its authors. Use permitted under Creative Commons License
Attribution 4.0 International (CC BY 4.0).</p>
      <p>resources for other languages remain scarce. To the best
of our knowledge, only a few works exist for Italian. In
[11], the authors use the CorEA corpus of user comments
(support or attack), to pairs of arguments. In [12], the
authors propose a new model for stance detection, trained
and evaluated on a corpus of Italian tweets where users
were discussing on a highly polarized political debate.</p>
      <p>Among the many domains of interest for argument
mining, our focus is on the legal domain, where
argumentation is fundamental for the decision-making process.</p>
      <p>
        Legal reasoning relies heavily on well-structured
arguments, as legal professionals must construct and
deconstruct arguments within formal documents, providing
a challenging setting for assessing an LLMs’ ability to
engage in complex reasoning tasks. Despite its relevance,
little attention has been given to argument mining in
the legal domain in Italian. Most existing work in legal
NLP for Italian has focused on tasks such as law article
retrieval [13, 14], outcome prediction [
        <xref ref-type="bibr" rid="ref5">15</xref>
        ], analysis of
contracts [
        <xref ref-type="bibr" rid="ref6 ref7">16, 17</xref>
        ], and summarization [
        <xref ref-type="bibr" rid="ref8 ref9">18, 19</xref>
        ].
      </p>
      <p>
        Our challenge for CALAMITA [
        <xref ref-type="bibr" rid="ref10">20</xref>
        ] consists of three
classification tasks over argumentative texts. We mostly
pus for argument mining on legal documents in English.
      </p>
      <p>Since we leverage real legal documents, not synthetic or
artificially constructed case studies, our dataset reflects
the real complexity and nuances of legal argumentation.</p>
      <p>It is therefore particularly relevant for a robust
assessment of LLMs’ abilities in real-world applications. To
the best of our knowledge, we are the first to propose a
challenge of argument mining over legal documents in
Italian.</p>
      <p>
        The challenge requires understanding not only the
have been developed over the last decade [6, 7, 8, 9, 10], follow the setting used in Demosthenes [
        <xref ref-type="bibr" rid="ref11 ref12">21, 22</xref>
        ], a
corItalian language but domain-specific technical language.
      </p>
      <p>
        Such a language uses complex syntactic structures, and a
specialized terminology. Besides language, the challenge
tests LLMs’ ability to recognize and interpret legal
arguments by recognizing typical argumentation schemes
[
        <xref ref-type="bibr" rid="ref13">23</xref>
        ], e.g., patterns of reasoning used in human discourse,
ofering a principled approach to argument analysis and
evaluation. Identifying schemes is challenging as there
are many possible schemes, and arguments are often only
partially laid out in the text, leaving many important
parts implicit for brevity or because they are considered
common knowledge. Nonetheless, this task lends itself
to generalization beyond the legal domain, making the
insights transferable to other fields where structured
reasoning plays a critical role.
      </p>
    </sec>
    <sec id="sec-3">
      <title>2. Challenge: Description</title>
      <sec id="sec-3-1">
        <title>Si osserva poi che ritenere che la mancata</title>
        <p>possibilità di detrazione a favore di soggetti
come il ricorrente comporti un aiuto di Stato
in favore degli ospedali pubblici, in quanto
le perdite degli stessi vengono ripianate dalle
USL e dalla Regioni trascura di considerare
l’accessibilità, indiscriminata, ai servizi dei
nosocomi pubblici da parte dei soggetti iscritti
al SSN, rispetto a quella ad un libero
professionista sanitario che, in quanto tale, ben
potrebbe rifiutarsi di prestare i propri servigi
al pare di un normale contraente.
• Argument conclusion: the statement that follows
logically from the premise(s) and represents the
ifnal point being argued for.</p>
      </sec>
      <sec id="sec-3-2">
        <title>Dunque, l’uficio ha riconosciuto la non imponibilità IVA delle cessioni all’esportazione, così cessando sul punto la materia del contendere.</title>
        <p>We consider an argument as a set of interconnected
portions of texts called argument components. The
connections between components form a specific pattern of Argument components can be involved in more than
relationships that represents a reasoning paradigm. one relationship, therefore a component may be the
con</p>
        <p>The following tasks presume that argument compo- clusions of other premises, as well as a premise of other
nents have already been identified from the source doc- arguments. In that case, the component is to be classified
uments. Argument components can therefore be clas- as a premise.
sified according to their role in the connections (such
as Premises or Conclusions), according to their content Premise Type classification. Multi-label
classifica(such as Legal or Factual), and according to the rela- tion: classify an argumentative premise as factual or legal
tionship pattern they contribute to (the Argumentative (or both).</p>
        <p>Scheme).</p>
        <p>This challenge proposes three classification tasks, in
the context of argument mining in the legal domain:
• Factual premise: a premise that describes factual
situations and events, pertaining to the substance
or the procedure of the case.
• Argument Component classification : given
an argumentative component, classify it as
premise or conclusion.
• Premise Type classification : given a premise,</p>
        <p>classify it as factual or legal.
• Argument Scheme classification : given a
predetermined set of argument schemes, classify a
legal premise as belonging to one or more such
schemes.</p>
        <p>The following paragraphs contain a definition of each
class, along with an example extracted from the dataset.</p>
        <p>The translated version of the examples is available in
Appendix A.</p>
        <p>Argument Component classification. Binary
classiifcation: given an argumentative component, classify it
as premise or conclusion.</p>
        <p>Indubbiamente, la contribuente ha impugnato
la sentenza di prime cure, rappresentando
nuovamente di non aver potuto proporre appello
avverso la pronuncia di condanna di primo
grado, per causa di forza maggiore.
• Legal premise: a premise that specifies the legal
content (legal rules, precedents, interpretation of
applicable laws and principles).</p>
        <p>La giurisprudenza citata, alla motivazione
della quale si fa rinvio, ha tra l’altro preso
posizione espressamente e positivamente sulla
conformità della normativa italiana rispetto
a quella dell’Unione Europea, risultando così
confutata anche la doglianza della difesa sul
punto che ha chiesto la sospensione del
procedimento, con investitura della Corte di Giustizia</p>
      </sec>
      <sec id="sec-3-3">
        <title>Europea della questione.</title>
        <p>• Argument premise: a proposition that provides a
reason or support for the argument.</p>
        <p>Since a premise could be both factual and legal, this task
is framed as multi-label binary classification.</p>
        <p>Argument Scheme classification. Legal premises
determine the nature of the legal reasoning they support,
hence they are labeled with the corresponding reasoning
pattern, called argument scheme. We define five schemes
relevant for tax law. Each legal premise may be assigned
multiple schemes, therefore we frame this task as
multilabel multi-class classification.</p>
        <p>Given a legal premise, classify it as belonging to one or
more of the following schemes: (established) rule,
precedent, classification , interpretative, or principle.
• Rule (or established rule) scheme: it is used
whenever an explicit reference to codified law is
present. This reference can be the reference to
a certain article or the quotation of the text of a
certain article.</p>
        <p>Infatti, è ben vero che, ai sensi del
combinato disposto dagli articoli 54 e 23 D.Lgs. n.
546/1992, il convenuto in appello deve
costituirsi entro 60 giorni dal giorno in cui ricorso
è stato notificato.
• Precedent scheme: it is used whenever there is
an explicit reference to a previous decision. In
the dataset we considered only the references to
a decision of both the Court of Cassation or the
European Court of Justice.</p>
        <p>L’ Amministrazione “ha l’onere di provare ed
allegare gli elementi probatori su cui si fondi
la contestazione, tra i quali possono rilevare,
in via indiziaria, quali elementi sintomatici
della mancata esecuzione della prestazione dal
fatturante, l’assenza della minima dotazione
personale e strumentale, l’immediatezza dei
rapporti (cedente/prestatore fatturante
interposto e cessionario/committente), una
conclamata inidoneità allo svolgimento dell’attività
economica e la non corrispondenza tra i
cedenti e la società coinvolta nell’operazione”.
con incarico a terzi) e cedere il prodotto finito
ottenuto.
• Interpretative scheme: it is used whenever the
Court expresses new interpretative assertions
(that may depend on previous case law) thereby
creating new precedents.</p>
        <p>Si vuole dire, in sostanza, che la finalità del
contraddittorio anticipato è quella di mettere
il contribuente nella condizione di potere fare
valere le proprie osservazioni prima che la
decisione sia adottata e, quindi, di far sì che
l’Amministrazione possa tener conto di tutti gli
elementi del caso nell’adottare (o non adottare)
il provvedimento ovvero nel dare a questo un
contenuto piuttosto che un altro.
• Principle scheme: it is used whenever the Court
explicitly refers to a principle of law (e.g. the
Principle of proportionality).</p>
        <p>Nell’ordinamento unionale, pertanto, il
principio del contraddittorio in ambito tributario
prescinde dalla natura del tributo e deve
trovare applicazione ogni qualvolta
l’amministrazione sulla base della documentazione
esibita ritenga dovere dare alla stessa
documentazione interpretazione diversa da quella data
dal contribuente invitandolo, come detto, a
fornire nel corso del contraddittorio le ragioni
della propria scelta.</p>
      </sec>
    </sec>
    <sec id="sec-4">
      <title>3. Data description</title>
      <sec id="sec-4-1">
        <title>3.1. Origin of data</title>
        <p>In conclusione, per quanto fin qui esposto, i
“compro oro” possono essere definiti come
“esercizi commerciali che acquistano, commerciano
o rivendono oggetti d’oro, di metalli preziosi o
recanti pietre preziose usati e li cedono nella
forma di materiale, di rottami d’oro o di
metalli preziosi alle fonderie o ad altre aziende
specializzate nel recupero di materiali preziosi”.</p>
        <sec id="sec-4-1-1">
          <title>Trattano esclusivamente prodotti finiti e non possono, congiuntamente, acquistare oro da gioielleria usato, fonderlo (per proprio conto o</title>
          <p>The data consists of argumentative portions of text
extracted from 225 Italian decisions on Value Added Tax
(VAT) by the Regional Tax Commissions from various
judicial districts. The decisions were downloaded
par• Classification scheme : it is used whenever a legal tially from the open Giustizia Tributaria database1 and
concept is defined, its properties are listed, and from other judicial databases accessed through university
a certain fact or legal deed must be qualified as licensing agreements. The decisions range from 2010 to
having those properties. 2022 and concern taxable transactions, exemptions,
outof-scope transactions, and the right to obtain a deduction.</p>
          <p>The argumentative components were extracted from the
sections “Motivi della decisione”, “Diritto” or “Fatto e
diritto”, depending on the format of each decision.</p>
          <p>The collected data were anonymised modifying any
identification data of natural or legal persons involved in
the proceedings. In particular, the names of the parties
in the proceeding and, to provide the highest privacy
standards, also the names of the companies have been
replaced with initials (e.g., Mario Rossi in “MR”, Company
1Tax Justice database accessible at: https://www.giustizia-tributaria.
it/.
s.r.l in “C s.r.l.”). The names of the judges composing the
judicial panel have been replaced by “giu1, giu2, [...]
giuN”. Also, addresses and places were replaced with
’XXX’, and dates were changed to show only the year in
the following format: DD/MM/2015.
set, some of which are included in Section 2. Here we
report the zero-shot version. The translation of the
zeroshot prompts is available in Appendix B. The few-shot
version is available in Appendix C.</p>
        </sec>
      </sec>
      <sec id="sec-4-2">
        <title>3.2. Annotation details</title>
        <p>
          The dataset was annotated by four tax law experts.
Annotation guidelines are significantly based on our previous
work on the Demosthenes corpus [
          <xref ref-type="bibr" rid="ref11">21</xref>
          ], a dataset with
English documents from the Court of Justice of the
European Union. The guidelines were adapted to the Italian
decisions, and refined through an iterative process of
validation and discussion, to solve conflicts between an- Premise Type classification: given a premise, classify
notators. In particular, the annotation is based on the it as factual, legal or both.
same classes used in Demosthenes. However, the struc- Prompt: “Classifica la seguente premessa come di fatto
ture of the decisions is diferent: while in the English ‘F’, legale ‘L’ o entrambe. Le premesse di fatto (F) descrivono
corpus the annotation is done at the sentence level, it situazioni ed eventi fattuali relativi al caso di specie. Le
preis not always possible to meet this criterion in Italian messe legali (L) specificano il contenuto giuridico (norme
decisions. Therefore, the constraint has been relaxed, giuridiche, precedenti, interpretazione delle leggi e dei
prinallowing a single annotation to cover multiple sentences cipi applicabili). L’output atteso è una lista con tutte le
and a single sentence to contain multiple annotations. label applicabili. Ad esempio: [‘F’, ‘L’]. Testo: ”
The tagged decisions are available in our GitHub
repository. 2
Argument Component classification: given an
argumentative text, classify it as premise or conclusion.
        </p>
        <sec id="sec-4-2-1">
          <title>Prompt: “Classifica il seguente testo argomentativo come</title>
          <p>premessa ‘prem’ o conclusione ‘conc’. Per premessa (prem)
si intende una proposizione che fornisce una ragione o un
supporto per l’argomentazione. Per conclusione (conc) si
intende l’afermazione che segue logicamente dalle premesse
e rappresenta il punto finale che viene argomentato. Testo: ”
Argument Scheme classification: given a legal
premise, classify it as one or more of the following
argu3.3. Data format mentative schemes: Rule, Prec, Class, Itpr, Princ.
Data are available as a Hugging Face Dataset,3 divided in Prompt: “Classifica la seguente premessa legale in uno
three splits: train, val and test. Each row represents an o più dei seguenti schemi argomentativi: Rule, Prec, Class,
argumentative component, with the following columns: Itpr, Princ. Rule: se esiste un riferimento esplicito o
implicito a un articolo di legge o la citazione del testo di una
• Text: the text of the component norma. Prec: se esiste un riferimento ad una precedente
• Document: the document it belongs to pronuncia della Corte di Cassazione o della Corte di
Gius• Component: if it is a premise (prem) or a conclu- tizia dell’Unione Europea. Class: se c’è la definizone di un
sion (conc) concetto giuridico o degli elementi costitutivi dello stesso.
• Type: a list value representing the type of a Itpr: se c’è il riferimento a uno dei criteri interpretativi
premise; the list contains F for a Factual premise contenuti all’art. 12 delle preleggi (letterale, teleologica,
and L for a Legal one. psicologica, sistematica) al codice civile. Princ: se c’è un
• Scheme: a list value representing the argumenta- riferimento espresso a un prinicpio generale del diritto (es.
tive schemes of a legal premise. The values are: principio di proporzionalità). L’output atteso è una lista
Rule, Prec, Class, Itpr and Princ. con tutte le label applicabili. Ad esempio: [‘Prec’, ‘Princ’,
• Chain_id: univocal for each document, it specifies ‘Rule’]. Testo: ”
the argumentative chain the component belongs
to (e.g. A1, A2,..., B1, B2,...) 3.5. Detailed data statistics
• Id: an univocal numerical id</p>
        </sec>
      </sec>
      <sec id="sec-4-3">
        <title>3.4. Example of prompts used for zero and few shots</title>
        <p>For each task, we propose both a zero-shot and a few-shot
prompt. For the few-shot version, we have selected some
particularly representative examples from the training
2https://github.com/adele-project/AMELIA/
3https://huggingface.co/datasets/nlp-unibo/AMELIA
The composition of the dataset is summarized in Table
1. The splitting between train, validation, and test data
was done at the document level so that components of
the same document belong to the same split. It was
performed manually, with a ratio of approximately 60:20:20,
and the aim of balancing the Scheme classes as much as
possible. We adopt the train/val/test format to make the
results comparable with as many methods as possible,
such as fine-tuned transformer-based models.</p>
        <p>Split</p>
        <p>N docs</p>
        <p>Train
Validation</p>
        <p>Test
Total
Prem</p>
      </sec>
    </sec>
    <sec id="sec-5">
      <title>4. Metrics</title>
      <p>capture or leverage such contextual details that would
otherwise aid in more accurate argument classification.</p>
      <p>Due to the heavy unbalance between the classes, we eval- Another limitation is the manual annotation process,
uate the results using the macro F1 score. Additionally, which, despite eforts to ensure consistency through
we evaluate the F1 score of each class to provide further expert annotators and conflict resolution, may still be
insights. subject to human bias or interpretation inconsistencies.</p>
      <p>
        As a reference, in Demosthenes [
        <xref ref-type="bibr" rid="ref11">21</xref>
        ] the best macro F1 These subjective elements could afect the quality and
results for the three tasks are 0.88 for Argument Com- reproducibility of the tasks.
ponent classification, 0.85 for Premise Type
classification, and 0.75 for Argument Scheme classification. It is
important to specify that these scores are not directly 6. Ethical issues
comparable and we provide them only as a reference of
the dificulty of the tasks.
      </p>
      <p>The dataset comprises legal decisions that have been
anonymised to protect the privacy of the individuals.</p>
      <p>
        However, it is important to acknowledge the potential
5. Limitations risks related to re-identification, even with
anonymisation eforts, especially in legal contexts where case details
The original documents, along with the argument min- could be cross-referenced with external sources. Care
ing annotation, are already available as part of the Adele was taken to remove any personal identifiers, such as
tool.4 The original documents, annotated according to names, addresses, and dates, but residual risks may
rethe task of outcome prediction instead of argument min- main.
ing, are also published in [
        <xref ref-type="bibr" rid="ref5">15</xref>
        ]. Additionally, the use of this dataset raises questions
      </p>
      <p>The dataset is limited in size, consisting of only 225 regarding the deployment of AI systems in legal contexts.
legal decisions on Value Added Tax (VAT). While this AI used by a judicial authority in researching and
interprovides a valuable resource for testing argument min- preting facts and the law are considered high-risk by the
ing models in the Italian tax legal domain, the relatively AI Act.5 Those systems must conform to the essential
small dataset may not capture the full diversity of argu- requirements (e.g. data governance, user transparency,
mentative structures present in the broader Italian tax human oversight, etc.) and the conformity must be
doculegal system or other legal domains. This could limit mented.
the scalability of models trained on this dataset. Also, Finally, a critical aspect is the transparency and
acgiven that the legal decisions are from a specific time countability of AI systems when applied in sensitive
doframe (2010-2022), the dataset may not reflect more re- mains like law. Users of the models should understand
cent developments or changes in legal reasoning or tax their limitations, especially in tasks involving nuanced
law. reasoning like legal argumentation. Furthermore,
ensur</p>
      <p>Secondly, the dataset has been anonymised to protect ing that legal professionals and stakeholders have the
the privacy of individuals and legal entities. While this ability to audit and interpret the decisions made by AI
is necessary to comply with data protection regulations, models is crucial to avoid undermining trust in legal
inthe anonymisation process may have removed certain stitutions.
contextual details (e.g., names of places or entities) that
could be relevant for understanding the nuances of
certain legal arguments. As a result, models may not fully
4https://adele-tool.eu/
5https://eur-lex.europa.eu/eli/reg/2024/1689/oj.</p>
    </sec>
    <sec id="sec-6">
      <title>7. Data license and copyright issues</title>
      <p>[5] J. Lawrence, C. Reed, Argument Mining: A
Survey, Computational Linguistics 45 (2020) 765–818.
doi:10.1162/coli_a_00364.</p>
      <p>The dataset used in this challenge consists of legal deci- [6] I. Habernal, D. Faber, N. Recchia, S. Bretthauer,
sions on Value Added Tax (VAT) made by the Regional I. Gurevych, I. S. genannt Döhmann, C. Burchard,
Tax Commissions in Italy, available and downloaded from Mining legal arguments in court decisions, Artif.
the Giustizia Tributaria and other judicial databases ac- Intell. Law 32 (2024) 1–38.
cessed through university licensing agreements. These [7] V. Niculae, J. Park, C. Cardie, Argument mining
legal texts, being oficial public documents, are generally with structured svms and rnns, in: ACL (1),
Asnot subject to copyright restrictions. The dataset con- sociation for Computational Linguistics, 2017, pp.
sists of a non-substantial part of the respective databases. 985–995.</p>
      <p>Moreover, the use of data is compliant with the text and [8] P. Poudyal, J. Savelka, A. Ieven, M. F. Moens,
data mining exception under the EU Copyright Directive T. Goncalves, P. Quaresma, ECHR: Legal corpus
and implementing national law.6 for argument mining, in: E. Cabrio, S. Villata</p>
      <p>Since the data has been processed and annotated, the (Eds.), Proceedings of the 7th Workshop on
Arannotations and derived data are subject to copyright by gument Mining, Association for Computational
the authors of this challenge. To promote transparency Linguistics, Online, 2020, pp. 67–75. URL: https:
and further research, the dataset is released under the //aclanthology.org/2020.argmining-1.8.
Creative Commons Attribution 4.0 International (CC BY [9] T. Mayer, S. Marro, E. Cabrio, S. Villata, Enhancing
4.0) license. This license allows others to share, use, and evidence-based medicine with natural language
aradapt the data, as long as appropriate credit is given to the gumentative analysis of clinical trials, Artif. Intell.
creators, and any modifications are explicitly indicated. Medicine 118 (2021) 102098.
[10] P. Accuosto, H. Saggion, Mining arguments in
scientific abstracts with discourse-level embeddings,
Acknowledgments Data Knowl. Eng. 129 (2020) 101840.
[11] P. Basile, V. Basile, E. Cabrio, S. Villata, Argument
This work was partially supported by the following Mining on Italian News Blogs, volume 1749 of CEUR
projects: “ADELE – Analytics for DEcision of LEgal cases” Workshop Proceedings, CEUR-WS.org, 2016. URL:
(Justice Programme, GA. No. 101007420); PRIN2022 https://ceur-ws.org/Vol-1749/paper8.pdf.
PRIMA - PRivacy Infringements Machine-Advice (Ref. [12] M. Lai, V. Patti, G. Rufo, P. Rosso, Stance evolution
Prot. n.: 20224TPEYC - CUP J53D23005130001); “FAIR - and twitter interactions in an italian political debate,
Future Artificial Intelligence Research” – Spoke 8 “Perva- in: M. Silberztein, F. Atigui, E. Kornyshova, E.
Mésive AI’’, under the European Commission’s NextGener- tais, F. Meziane (Eds.), Natural Language Processing
ation EU programme, PNRR – M4C2 – Investimento 1.3, and Information Systems, Springer International
Partenariato Esteso (PE00000013). Publishing, Cham, 2018, pp. 15–27.
[13] A. Tagarelli, A. Simeri, Unsupervised law article
References mining based on deep pre-trained language
representation models with application to the italian
civil code, Artificial Intelligence and Law 30 (2021)
417–473. doi:10.1007/s10506- 021- 09301- 8.</p>
    </sec>
    <sec id="sec-7">
      <title>A. Translated Examples</title>
      <p>Argument Scheme classification.</p>
      <p>It should be noted that viewing the inability to deduct
expenses for individuals such as the plaintif as state
aid to public hospitals overlooks the indiscriminate
accessibility of public hospital services for individuals
registered with the National Health Service (SSN). In
contrast, a self-employed healthcare professional may
refuse to provide services as an ordinary contractor.</p>
      <sec id="sec-7-1">
        <title>Thus, the ofice recognized the VAT non-taxable nature of the exportation, thus considering there is no longer any grounds to proceed on the matter.</title>
      </sec>
      <sec id="sec-7-2">
        <title>Undoubtedly, the taxpayer appealed the first instance ruling, again representing that she could not appeal against the first instance decision due to force majeure.</title>
      </sec>
      <sec id="sec-7-3">
        <title>The cited case law, to which reference is made for</title>
        <p>its reasoning, has explicitly and positively addressed
the conformity of Italian legislation with that of the</p>
      </sec>
      <sec id="sec-7-4">
        <title>European Union. This efectively refutes the defense’s</title>
        <p>objection on this point, which requested the suspension
of the proceedings and the referral of the issue to the</p>
      </sec>
      <sec id="sec-7-5">
        <title>European Court of Justice.</title>
      </sec>
      <sec id="sec-7-6">
        <title>In fact, it is true that under Articles 54 and 23 of</title>
      </sec>
      <sec id="sec-7-7">
        <title>Legislative Decree No. 546/1992, the defendant on</title>
        <p>appeal must come up for trial within 60 days from the
day on which appeal was served.</p>
        <p>The Administration “has the burden of proving and
attaching the evidence on which the dispute is based,
among which the absence of the minimum personal
and instrumental equipment, the immediacy of the
relationships (transferor/interposed invoicing provider
and transferee/buyer), an overt unsuitability to carry
out the economic activity and the mismatch between
the transferors and the company involved in the
transaction may be circumstantial.”
Classification Scheme:
In conclusion, given what has been said so far, “gold
shop” can be defined as “business establishments that
buy, trade or resell used objects of gold, precious
metals or bearing precious stones and dispose of them in
the form of material, scrap gold or precious metals to
foundries or other companies specialising in the
recovery of precious materials”. They deal only in finished
products and may not purchase used jewelery gold,
melt it down (for their account or by commissioning
a third party) and dispose of the resulting finished
product.</p>
        <p>Interpretative Scheme:
It means that, in essence, the purpose of the right
to be heard is to put the taxpayer in the position of
being able to make his or her observations before the
decision is made and, therefore, to ensure that the
administration can take into account all the elements
of the case in adopting (or not adopting) the measure
or in giving this one content rather than another.
Principle Scheme:
In the European Union system, therefore, the right to
be heard in tax matters is independent of the nature
of the tax and must be applied whenever the
administration on the basis of the documentation exhibited
deems it necessary to give the same documentation
an interpretation that difers from that given by the
taxpayer, inviting him, as mentioned, to provide in
the exercise of the right to be heard the reasons for his
choice.</p>
      </sec>
    </sec>
    <sec id="sec-8">
      <title>B. Translated Prompts</title>
      <p>Argument Component classification.</p>
      <p>“Classify the following argumentative text as
premise ‘prem’ or conclusion ‘conc’. A premise
(prem) is a proposition that provides a reason or
support for the argument. A conclusion (conc) is the
statement that follows logically from the premise(s)
and represents the final point being argued for.</p>
      <p>Text:”
Premise Type classification.</p>
      <p>“Classify the following premise as factual ‘F’, legal
‘L’ or both. Factual premises (F) describe factual
situations and events, pertaining to the substance or the
procedure of the case. Legal premises (L) specify the
legal content (legal rules, precedents, interpretation
of applicable laws and principles). The expected
output is a list with all applicable labels. For example:
[‘F’, ‘L’]. Text:”</p>
      <p>“Classify the following legal premise as one or more
of the following argumentative schemes: Rule, Prec,
Class, Itpr, Princ. Rule: whether there is an explicit
or implicit reference to an article of law or citation
of the text of a certain article. Prec: whether there
is a reference to a previous ruling of the Supreme
Court or the Court of Justice of the European Union.
Class: if there is a definition of a legal concept or
its constituent elements. Itpr: if there is reference
to one of the interpretative criteria contained in
Article 12 of the prelegislations (literal, teleological,
psychological, systematic) to the Civil Code. Princ:
if there is a reference to a general principle of law
(e.g. principle of proportionality). The expected
output is a list with all applicable labels. For example:
[‘Prec’, ‘Princ’, ‘Rule’]. Text:”</p>
    </sec>
    <sec id="sec-9">
      <title>C. Few-shot prompts</title>
      <p>Argument Component classification.
“Classifica il seguente testo argomentativo come
premessa ‘prem’ o conclusione ‘conc’. Per premessa
(prem) si intende una proposizione che fornisce
una ragione o un supporto per l’argomentazione.
Per conclusione (conc) si intende l’afermazione che
segue logicamente dalle premesse e rappresenta il
punto finale che viene argomentato.</p>
      <p>Esempi:
Testo: Si osserva poi che ritenere che la mancata
possibilità di detrazione a favore di soggetti come il
ricorrente comporti un aiuto di Stato in favore degli
ospedali pubblici, in quanto le perdite degli stessi
vengono ripianate dalle USL e dalla Regioni trascura di
considerare l’accessibilità, indiscriminata, ai servizi
dei nosocomi pubblici da parte dei soggetti iscritti
al SSN, rispetto a quella ad un libero professionista
sanitario che, in quanto tale, ben potrebbe rifiutarsi
di prestare i propri servigi al pare di un normale
contraente
Risposta: prem
Risposta: conc
Testo: L’appello è infondato e va respinto
Testo: Va osservato che la motivazione dell’atto di
accertamento non può esaurirsi nel rilievo dello
scostamento, ma deve essere integrata con la
dimostrazione dell’applicabilità in concreto dello
‘standard’ prescelto e con le ragioni per le quali sono state
disattese le contestazioni sollevate dal contribuente.
(cfr. Cass. S.U. 26635/2009, Cass. 12558/2010, Cass.
12428/2012, Cass. 23070/2012)
Testo: Dunque, l’uficio ha riconosciuto la non
imponibilità IVA delle cessioni all’esportazione, così
cessando sul punto la materia del contendere
Testo: Risulta d’altronde dalle osservazioni scritte
del governo spagnolo che quest’ultimo non riesce
a discernere tale diferenza ad un esame delle
pertinenti norme dell’ordinamento spagnolo.
Testo: Il Collegio, esaminata l’eccezione preliminare
svolta nel suo appello dall’Uficio e relativa alla
richiesta nullità della sentenza per mancata instaurazione
del contraddittorio, la respinge</p>
      <p>“Classifica la seguente premessa come di fatto ‘F’,
legale ‘L’ o entrambe. Le premesse di fatto (F)
descrivono situazioni ed eventi fattuali relativi al caso
di specie. Le premesse legali (L) specificano il
contenuto giuridico (norme giuridiche, precedenti,
interpretazione delle leggi e dei principi applicabili).
L’output atteso è una lista con tutte le label
applicabili. Ad esempio: [‘F’, ‘L’].
Testo: Per i primi giudici nel caso di specie questa
esenzione non poteva essere applicata perché la
complessiva attività di ‘A’ srl era un’attività commerciale
svolta in concorrenza con altre imprese operanti nel
settore
Risposta: [‘F’]
Testo: In assenza di sifatti elementi, che in via
presuntiva avrebbero potuto fare giungere questo
giudice a conclusioni diverse in via logica, si deve
confermare l’esito cui è giunta la commissione
provinciale
Risposta: [‘F’]
Testo: Su questo si osserva che si deve condividere
la circostanza dedotta dal giudice di prime cure per
cui deve essere il contribuente, ove sia contestata la
inerenza e verità della rappresentazione ricavabile
dal documento contabile, a dare la dimostrazione
della fondatezza e della correttezza del
comportamento tenuto
Risposta: [‘L’]
Testo: L’Uficio non potrà impedire ad un
imprenditore, per esempio, di cedere immobili con prezzi
bassi onulli per ricavare liquidità a fronte di nuovi
impegni, ma dovrà rilevare la condotta
antieconomica dello stesso sulla base dell’utile di esercizio
Risposta: [‘L’]
Testo: Invero l’avviso di accertamento è fondato
sul mancato rispetto, da parte del contribuente, nel
calcolo del ROL, delle disposizioni dell’articolo 96,
secondo comma, del TUIR, che ne definisce le
modalità
Risposta: [‘F’, ‘L’]
Testo: La società ‘A’, per quanto previsto dall’art.
4, comma 18 del Regolamento CEE n. 2913/1992,
riveste il ruolo di ‘dichiarante in Dogana‘, soggetto
passivo della obbligazione
Risposta: [‘F’, ‘L’]</p>
      <p>“Classifica la seguente premessa legale in uno o più
dei seguenti schemi argomentativi: Rule, Prec, Class,
Itpr, Princ. Rule: se esiste un riferimento
esplicito o implicito a un articolo di legge o la citazione
del testo di una norma. Prec: se esiste un
riferimento ad una precedente pronuncia della Corte di
Cassazione o della Corte di Giustizia dell’Unione
Europea. Class: se c’è la definizone di un concetto
giuridico o degli elementi costitutivi dello stesso.
Itpr: se c’è il riferimento a uno dei criteri
interpretativi contenuti all’art. 12 delle preleggi (letterale,
teleologica, psicologica, sistematica) al codice civile.
Princ: se c’è un riferimento espresso a un prinicpio
generale del diritto (es. principio di
proporzionalità). L’output atteso è una lista con tutte le label
applicabili. Ad esempio: [‘Prec’, ‘Princ’, ‘Rule’].
Testo: Infatti, è ben vero che, ai sensi del combinato
disposto dagli articoli 54 e 23 D.Lgs. n. 546/1992, il
convenuto in appello deve costituirsi entro 60 giorni
dal giorno in cui ricorso è stato notificato.</p>
      <p>Risposta: [‘Rule’]
Testo: L’Amministrazione “ha l’onere di provare
ed allegare gli elementi probatori su cui si fondi la
contestazione, tra i quali possono rilevare, in via
indiziaria, quali elementi sintomatici della mancata
esecuzione della prestazione dal fatturante, l’assenza
della minima dotazione personale e strumentale,
l’immediatezza dei rapporti (cedente/prestatore
fatturante interposto e cessionario/committente), una
conclamata inidoneità allo svolgimento dell’attività
economica e la non corrispondenza tra i cedenti e
la società coinvolta nell’operazione”
Testo: In conclusione, per quanto fin qui esposto, i
“compro oro” possono essere definiti come “esercizi
commerciali che acquistano, commerciano o
rivendono oggetti d’oro, di metalli preziosi o recanti pietre
preziose usati e li cedono nella forma di materiale, di
rottami d’oro o di metalli preziosi alle fonderie o ad
altre aziende specializzate nel recupero di materiali
preziosi”. Trattano esclusivamente prodotti finiti
e non possono, congiuntamente, acquistare oro da
gioielleria usato, fonderlo (per proprio conto o con
incarico a terzi) e cedere il prodotto finito ottenuto
Risposta: [‘Class’]
Testo: Si vuole dire, in sostanza, che la finalità del
contraddittorio anticipato è quella di mettere il
contribuente nella condizione di potere fare valere le
proprie osservazioni prima che la decisione sia
adottata e, quindi, di far sì che l’Amministrazione possa
tener conto di tutti gli elementi del caso nell’adottare
(0 non adottare) il provvedimento ovvero nel dare a
questo un contenuto piuttosto che un altro.
Risposta: [‘Itpr’]
Testo: Nell’ordinamento unionale, pertanto, il
principio del contraddittorio in ambito tributario
prescinde dalla natura del tributo e deve trovare
applicazione ogni qualvolta l’amministrazione sulla base
della documentazione esibita ritenga dovere dare
alla stessa documentazione interpretazione diversa
da quella data dal contribuente invitandolo, come
detto fornire nel corso del contraddittorio le ragioni
della propria scelta
Risposta: [‘Princ’]
Testo: In sintesi per esterovestizione si intende la
ifttizia localizzazione della residenza fiscale di un
soggetto all’estero, in particolare in un Paese con
un trattamento fiscale più vantaggioso di quello
nazionale,che la giurisprudenza configura in termini
di abuso del diritto riconosciuto, in via tendenziale,
come principio generale anche nel diritto dei singoli
Stati membri (v. Cass., Sez. Un., n. 30055 del 2008,
secondo la quale il divieto di abuso del diritto si
traduce in un principio generale antielusivo che trova
fondamento, in tema di tributi non armonizzati, nei
principi costituzionali di capacità contributiva e di
progressività dell’imposizione).</p>
      <p>Risposta: [‘Prec’, ‘Class’, ‘Princ’]
Testo: La denuncia, infatti, non codificata nel codice
di procedura penale (a diferenza della notizia di
reato di cui all’articolo 347 c.p.p.), può definirsi come
qualunque atto con il quale chiunque abbia notizia di
un reato perseguibile d’uficio ne informa il pubblico
ministero o un uficiale di polizia giudiziaria.</p>
    </sec>
  </body>
  <back>
    <ref-list>
      <ref id="ref1">
        <mixed-citation>
          [1]
          <string-name>
            <given-names>E. M.</given-names>
            <surname>Bender</surname>
          </string-name>
          ,
          <string-name>
            <given-names>T.</given-names>
            <surname>Gebru</surname>
          </string-name>
          ,
          <string-name>
            <given-names>A.</given-names>
            <surname>McMillan-Major</surname>
          </string-name>
          ,
          <string-name>
            <given-names>S.</given-names>
            <surname>Shmitchell</surname>
          </string-name>
          ,
          <article-title>On the dangers of stochastic parrots: Can language models be too big?</article-title>
          , in: FAccT, [14]
          <string-name>
            <given-names>V.</given-names>
            <surname>Bellandi</surname>
          </string-name>
          ,
          <string-name>
            <given-names>S.</given-names>
            <surname>Castano</surname>
          </string-name>
          ,
          <string-name>
            <given-names>P.</given-names>
            <surname>Ceravolo</surname>
          </string-name>
          , E. Damiani, ACM,
          <year>2021</year>
          , pp.
          <fpage>610</fpage>
          -
          <lpage>623</lpage>
          . A.
          <string-name>
            <surname>Ferrara</surname>
            ,
            <given-names>S.</given-names>
          </string-name>
          <string-name>
            <surname>Montanelli</surname>
            ,
            <given-names>S.</given-names>
          </string-name>
          <string-name>
            <surname>Picascia</surname>
            ,
            <given-names>A</given-names>
          </string-name>
          . Polimeno,
        </mixed-citation>
      </ref>
      <ref id="ref2">
        <mixed-citation>
          [2]
          <string-name>
            <given-names>D.</given-names>
            <surname>Walton</surname>
          </string-name>
          , Argumentation Theory:
          <string-name>
            <given-names>A</given-names>
            <surname>Very Short D. Riva</surname>
          </string-name>
          ,
          <article-title>Knowledge-based legal document</article-title>
          reIntroduction,
          <string-name>
            <surname>Springer</surname>
            <given-names>US</given-names>
          </string-name>
          , Boston, MA,
          <year>2009</year>
          , pp.
          <source>trieval: A case study on italian civil court de1-22</source>
          . doi:
          <volume>10</volume>
          .1007/978- 0-
          <fpage>387</fpage>
          - 98197-
          <issue>0</issue>
          _1. cisions, in: D.
          <string-name>
            <surname>Symeonidou</surname>
            ,
            <given-names>R.</given-names>
          </string-name>
          <string-name>
            <surname>Yu</surname>
            ,
            <given-names>D.</given-names>
          </string-name>
          <string-name>
            <surname>Ceolin</surname>
          </string-name>
          ,
        </mixed-citation>
      </ref>
      <ref id="ref3">
        <mixed-citation>
          [3]
          <string-name>
            <given-names>M.</given-names>
            <surname>Lippi</surname>
          </string-name>
          ,
          <string-name>
            <given-names>P.</given-names>
            <surname>Torroni</surname>
          </string-name>
          , Argumentation mining: State M.
          <string-name>
            <surname>Poveda-Villalón</surname>
            ,
            <given-names>D.</given-names>
          </string-name>
          <string-name>
            <surname>Audrito</surname>
            ,
            <given-names>L. D.</given-names>
          </string-name>
          <string-name>
            <surname>Caro</surname>
            ,
            <given-names>F.</given-names>
          </string-name>
          <article-title>Grasso, of the art and emerging trends</article-title>
          ,
          <source>ACM Trans</source>
          .
          <string-name>
            <surname>Internet R. Nai</surname>
            ,
            <given-names>E.</given-names>
          </string-name>
          <string-name>
            <surname>Sulis</surname>
            ,
            <given-names>F. J.</given-names>
          </string-name>
          <string-name>
            <surname>Ekaputra</surname>
            ,
            <given-names>O.</given-names>
          </string-name>
          <string-name>
            <surname>Kutz</surname>
          </string-name>
          , N. TroTechn.
          <volume>16</volume>
          (
          <year>2016</year>
          )
          <volume>10</volume>
          :
          <fpage>1</fpage>
          -
          <lpage>10</lpage>
          :
          <fpage>25</fpage>
          . doi:
          <volume>10</volume>
          .1145/2850417. quard (Eds.),
          <source>Companion Proceedings of the 23rd</source>
        </mixed-citation>
      </ref>
      <ref id="ref4">
        <mixed-citation>
          [4]
          <string-name>
            <given-names>E.</given-names>
            <surname>Cabrio</surname>
          </string-name>
          ,
          <string-name>
            <given-names>S.</given-names>
            <surname>Villata</surname>
          </string-name>
          ,
          <article-title>Five years of argument mining: International Conference on Knowledge Engineera data-driven analysis</article-title>
          ,
          <source>in: IJCAI, ijcai.org</source>
          ,
          <year>2018</year>
          , pp.
          <source>ing and Knowledge Management, Bozen-Bolzano</source>
          ,
          <fpage>5427</fpage>
          -
          <lpage>5433</lpage>
          . Italy,
          <source>September 26-29</source>
          ,
          <year>2022</year>
          , volume
          <volume>3256</volume>
          <source>of CEUR Workshop Proceedings, CEUR-WS.org</source>
          ,
          <year>2022</year>
          . URL: https://ceur-ws.
          <source>org/</source>
          Vol-
          <volume>3256</volume>
          /km4law2.pdf.
        </mixed-citation>
      </ref>
      <ref id="ref5">
        <mixed-citation>
          [15]
          <string-name>
            <given-names>F.</given-names>
            <surname>Galli</surname>
          </string-name>
          ,
          <string-name>
            <given-names>G.</given-names>
            <surname>Grundler</surname>
          </string-name>
          ,
          <string-name>
            <given-names>A.</given-names>
            <surname>Fidelangeli</surname>
          </string-name>
          ,
          <string-name>
            <given-names>A.</given-names>
            <surname>Galassi</surname>
          </string-name>
          ,
          <string-name>
            <given-names>F.</given-names>
            <surname>Lagioia</surname>
          </string-name>
          ,
          <string-name>
            <given-names>E.</given-names>
            <surname>Palmieri</surname>
          </string-name>
          ,
          <string-name>
            <given-names>F.</given-names>
            <surname>Ruggeri</surname>
          </string-name>
          , G. Sartor,
          <string-name>
            <given-names>P.</given-names>
            <surname>Torroni</surname>
          </string-name>
          ,
          <article-title>Predicting outcomes of italian VAT decisions</article-title>
          ,
          <source>in: JURIX</source>
          , volume
          <volume>362</volume>
          <source>of Frontiers in Artificial Intelligence and Applications</source>
          , IOS Press,
          <year>2022</year>
          , pp.
          <fpage>188</fpage>
          -
          <lpage>193</lpage>
          . doi:
          <volume>10</volume>
          .3233/FAIA220465.
        </mixed-citation>
      </ref>
      <ref id="ref6">
        <mixed-citation>
          [16]
          <string-name>
            <given-names>A.</given-names>
            <surname>Galassi</surname>
          </string-name>
          ,
          <string-name>
            <given-names>F.</given-names>
            <surname>Lagioia</surname>
          </string-name>
          ,
          <string-name>
            <given-names>A.</given-names>
            <surname>Jabłonowska</surname>
          </string-name>
          ,
          <string-name>
            <given-names>M.</given-names>
            <surname>Lippi</surname>
          </string-name>
          ,
          <article-title>Argument premise: Unfair clause detection in terms of service across multiple languages</article-title>
          ,
          <source>Artificial Intelligence and Law</source>
          (
          <year>2024</year>
          )
          <fpage>1</fpage>
          -
          <lpage>49</lpage>
          . doi:
          <volume>10</volume>
          .1007/s10506- 024- 09398- 7.
        </mixed-citation>
      </ref>
      <ref id="ref7">
        <mixed-citation>
          [17]
          <string-name>
            <given-names>K.</given-names>
            <surname>Drawzeski</surname>
          </string-name>
          ,
          <string-name>
            <given-names>A.</given-names>
            <surname>Galassi</surname>
          </string-name>
          ,
          <string-name>
            <given-names>A.</given-names>
            <surname>Jablonowska</surname>
          </string-name>
          ,
          <string-name>
            <given-names>F.</given-names>
            <surname>Lagioia</surname>
          </string-name>
          ,
          <string-name>
            <given-names>M.</given-names>
            <surname>Lippi</surname>
          </string-name>
          ,
          <string-name>
            <given-names>H.</given-names>
            <surname>Micklitz</surname>
          </string-name>
          , G. Sartor, G. Tagiuri,
          <string-name>
            <given-names>P.</given-names>
            <surname>Torroni</surname>
          </string-name>
          ,
          <article-title>A corpus for multilingual analysis of online terms of service</article-title>
          , in: NLLP@EMNLP, Association for Computational Linguistics,
          <year>2021</year>
          , pp.
          <fpage>1</fpage>
          -
          <lpage>8</lpage>
          . doi:
          <volume>10</volume>
          .18653/v1/
          <year>2021</year>
          .nllp-
          <volume>1</volume>
          .1. Argument conclusion:
        </mixed-citation>
      </ref>
      <ref id="ref8">
        <mixed-citation>
          [18]
          <string-name>
            <given-names>L.</given-names>
            <surname>Ragazzi</surname>
          </string-name>
          , G. Moro,
          <string-name>
            <given-names>S.</given-names>
            <surname>Guidi</surname>
          </string-name>
          , G. Frisoni,
          <article-title>Lawsuit: a large expert-written summarization dataset of italian constitutional court verdicts</article-title>
          ,
          <source>Artificial Intelligence and Law</source>
          (
          <year>2024</year>
          )
          <fpage>1</fpage>
          -
          <lpage>37</lpage>
          . doi:
          <volume>10</volume>
          .1007/ s10506- 024- 09414- w.
        </mixed-citation>
      </ref>
      <ref id="ref9">
        <mixed-citation>
          [19]
          <string-name>
            <given-names>D.</given-names>
            <surname>Licari</surname>
          </string-name>
          ,
          <string-name>
            <given-names>P.</given-names>
            <surname>Bushipaka</surname>
          </string-name>
          , G. Marino, G. Comandé, Premise Type classification.
          <source>T. Cucinotta</source>
          ,
          <article-title>Legal holding extraction from italian case documents using italian-legal-bert text sum- Factual premise: marization</article-title>
          ,
          <source>in: Proceedings of the Nineteenth International Conference on Artificial Intelligence and Law</source>
          , ICAIL '23,
          <string-name>
            <surname>Association</surname>
          </string-name>
          for Computing Machinery, New York, NY, USA,
          <year>2023</year>
          , p.
          <fpage>148</fpage>
          -
          <lpage>156</lpage>
          . doi:
          <volume>10</volume>
          .1145/3594536.3595177. Legal premise:
        </mixed-citation>
      </ref>
      <ref id="ref10">
        <mixed-citation>
          [20]
          <string-name>
            <given-names>G.</given-names>
            <surname>Attanasio</surname>
          </string-name>
          ,
          <string-name>
            <given-names>P.</given-names>
            <surname>Basile</surname>
          </string-name>
          ,
          <string-name>
            <given-names>F.</given-names>
            <surname>Borazio</surname>
          </string-name>
          ,
          <string-name>
            <given-names>D.</given-names>
            <surname>Croce</surname>
          </string-name>
          ,
          <string-name>
            <given-names>M.</given-names>
            <surname>Francis</surname>
          </string-name>
          ,
          <string-name>
            <given-names>J.</given-names>
            <surname>Gili</surname>
          </string-name>
          , E. Musacchio,
          <string-name>
            <given-names>M.</given-names>
            <surname>Nissim</surname>
          </string-name>
          ,
          <string-name>
            <given-names>V.</given-names>
            <surname>Patti</surname>
          </string-name>
          ,
          <string-name>
            <given-names>M.</given-names>
            <surname>Rinaldi</surname>
          </string-name>
          ,
          <string-name>
            <given-names>D.</given-names>
            <surname>Scalena</surname>
          </string-name>
          ,
          <article-title>CALAMITA: Challenge the Abilities of LAnguage Models in ITAlian</article-title>
          ,
          <source>in: Proceedings of the 10th Italian Conference on Computational Linguistics</source>
          (CLiC-it
          <year>2024</year>
          ), Pisa, Italy, December 4 - December 6,
          <year>2024</year>
          , CEUR Workshop Proceedings, CEUR-WS.org,
          <year>2024</year>
          .
        </mixed-citation>
      </ref>
      <ref id="ref11">
        <mixed-citation>
          [21]
          <string-name>
            <given-names>G.</given-names>
            <surname>Grundler</surname>
          </string-name>
          ,
          <string-name>
            <given-names>P.</given-names>
            <surname>Santin</surname>
          </string-name>
          ,
          <string-name>
            <given-names>A.</given-names>
            <surname>Galassi</surname>
          </string-name>
          ,
          <string-name>
            <given-names>F.</given-names>
            <surname>Galli</surname>
          </string-name>
          ,
          <string-name>
            <given-names>F.</given-names>
            <surname>Godano</surname>
          </string-name>
          ,
          <string-name>
            <given-names>F.</given-names>
            <surname>Lagioia</surname>
          </string-name>
          ,
          <string-name>
            <given-names>E.</given-names>
            <surname>Palmieri</surname>
          </string-name>
          ,
          <string-name>
            <given-names>F.</given-names>
            <surname>Ruggeri</surname>
          </string-name>
          , G. Sartor,
          <string-name>
            <given-names>P.</given-names>
            <surname>Torroni</surname>
          </string-name>
          ,
          <article-title>Detecting arguments in CJEU decisions on fiscal state aid</article-title>
          , in: G. Lapesa,
          <string-name>
            <given-names>J.</given-names>
            <surname>Schneider</surname>
          </string-name>
          ,
          <string-name>
            <given-names>Y.</given-names>
            <surname>Jo</surname>
          </string-name>
          , Rule Scheme: S. Saha (Eds.),
          <source>Proceedings of the 9th Workshop on Argument Mining, International Conference on Computational Linguistics</source>
          , Online and in Gyeongju,
          <source>Republic of Korea</source>
          ,
          <year>2022</year>
          , pp.
          <fpage>143</fpage>
          -
          <lpage>157</lpage>
          . URL: https: //aclanthology.org/
          <year>2022</year>
          .argmining-
          <volume>1</volume>
          .
          <fpage>14</fpage>
          .
        </mixed-citation>
      </ref>
      <ref id="ref12">
        <mixed-citation>
          [22]
          <string-name>
            <given-names>P.</given-names>
            <surname>Santin</surname>
          </string-name>
          ,
          <string-name>
            <given-names>G.</given-names>
            <surname>Grundler</surname>
          </string-name>
          ,
          <string-name>
            <given-names>A.</given-names>
            <surname>Galassi</surname>
          </string-name>
          ,
          <string-name>
            <given-names>F.</given-names>
            <surname>Galli</surname>
          </string-name>
          ,
          <string-name>
            <given-names>F.</given-names>
            <surname>La- Precedent Scheme</surname>
          </string-name>
          : gioia, E. Palmieri,
          <string-name>
            <given-names>F.</given-names>
            <surname>Ruggeri</surname>
          </string-name>
          , G. Sartor,
          <string-name>
            <given-names>P.</given-names>
            <surname>Torroni</surname>
          </string-name>
          ,
          <article-title>Argumentation structure prediction in CJEU decisions on fiscal state aid</article-title>
          , in: ICAIL, ACM,
          <year>2023</year>
          , pp.
          <fpage>247</fpage>
          -
          <lpage>256</lpage>
          .
        </mixed-citation>
      </ref>
      <ref id="ref13">
        <mixed-citation>
          [23]
          <string-name>
            <given-names>D.</given-names>
            <surname>Walton</surname>
          </string-name>
          ,
          <string-name>
            <given-names>C.</given-names>
            <surname>Reed</surname>
          </string-name>
          ,
          <string-name>
            <given-names>F.</given-names>
            <surname>Macagno</surname>
          </string-name>
          , Argumentation schemes, Cambridge University Press,
          <year>2008</year>
          .
        </mixed-citation>
      </ref>
    </ref-list>
  </back>
</article>