@inproceedings{siino-2024-mistral,
title = "Mistral at {S}em{E}val-2024 Task 5: Mistral 7{B} for argument reasoning in Civil Procedure",
author = "Siino, Marco",
editor = {Ojha, Atul Kr. and
Do{\u{g}}ru{\"o}z, A. Seza and
Tayyar Madabushi, Harish and
Da San Martino, Giovanni and
Rosenthal, Sara and
Ros{\'a}, Aiala},
booktitle = "Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.semeval-1.24/",
doi = "10.18653/v1/2024.semeval-1.24",
pages = "155--162",
abstract = "At the SemEval-2024 Task 5, the organizers introduce a novel natural language processing (NLP) challenge and dataset within the realm of the United States civil procedure. Each datum within the dataset comprises a comprehensive overview of a legal case, a specific inquiry associated with it, and a potential argument in support of a solution, supplemented with an in-depth rationale elucidating the applicability of the argument within the given context. Derived from a text designed for legal education purposes, this dataset presents a multifaceted benchmarking task for contemporary legal language models. Our manuscript delineates the approach we adopted for participation in this competition. Specifically, we detail the use of a Mistral 7B model to answer the question provided. Our only and best submission reach an F1-score equal to 0.5597 and an Accuracy of 0.5714, outperforming the baseline provided for the task."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="siino-2024-mistral">
<titleInfo>
<title>Mistral at SemEval-2024 Task 5: Mistral 7B for argument reasoning in Civil Procedure</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Siino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="given">Seza</namePart>
<namePart type="family">Doğruöz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harish</namePart>
<namePart type="family">Tayyar Madabushi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giovanni</namePart>
<namePart type="family">Da San Martino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Rosenthal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aiala</namePart>
<namePart type="family">Rosá</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>At the SemEval-2024 Task 5, the organizers introduce a novel natural language processing (NLP) challenge and dataset within the realm of the United States civil procedure. Each datum within the dataset comprises a comprehensive overview of a legal case, a specific inquiry associated with it, and a potential argument in support of a solution, supplemented with an in-depth rationale elucidating the applicability of the argument within the given context. Derived from a text designed for legal education purposes, this dataset presents a multifaceted benchmarking task for contemporary legal language models. Our manuscript delineates the approach we adopted for participation in this competition. Specifically, we detail the use of a Mistral 7B model to answer the question provided. Our only and best submission reach an F1-score equal to 0.5597 and an Accuracy of 0.5714, outperforming the baseline provided for the task.</abstract>
<identifier type="citekey">siino-2024-mistral</identifier>
<identifier type="doi">10.18653/v1/2024.semeval-1.24</identifier>
<location>
<url>https://aclanthology.org/2024.semeval-1.24/</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>155</start>
<end>162</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Mistral at SemEval-2024 Task 5: Mistral 7B for argument reasoning in Civil Procedure
%A Siino, Marco
%Y Ojha, Atul Kr.
%Y Doğruöz, A. Seza
%Y Tayyar Madabushi, Harish
%Y Da San Martino, Giovanni
%Y Rosenthal, Sara
%Y Rosá, Aiala
%S Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F siino-2024-mistral
%X At the SemEval-2024 Task 5, the organizers introduce a novel natural language processing (NLP) challenge and dataset within the realm of the United States civil procedure. Each datum within the dataset comprises a comprehensive overview of a legal case, a specific inquiry associated with it, and a potential argument in support of a solution, supplemented with an in-depth rationale elucidating the applicability of the argument within the given context. Derived from a text designed for legal education purposes, this dataset presents a multifaceted benchmarking task for contemporary legal language models. Our manuscript delineates the approach we adopted for participation in this competition. Specifically, we detail the use of a Mistral 7B model to answer the question provided. Our only and best submission reach an F1-score equal to 0.5597 and an Accuracy of 0.5714, outperforming the baseline provided for the task.
%R 10.18653/v1/2024.semeval-1.24
%U https://aclanthology.org/2024.semeval-1.24/
%U https://doi.org/10.18653/v1/2024.semeval-1.24
%P 155-162
Markdown (Informal)
[Mistral at SemEval-2024 Task 5: Mistral 7B for argument reasoning in Civil Procedure](https://aclanthology.org/2024.semeval-1.24/) (Siino, SemEval 2024)
ACL