@inproceedings{guimaraes-etal-2024-lisbon,
title = "Lisbon Computational Linguists at {S}em{E}val-2024 Task 2: Using a Mistral-7{B} Model and Data Augmentation",
author = "Guimar{\~a}es, Artur and
Martins, Bruno and
Magalh{\~a}es, Jo{\~a}o",
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-1.185",
doi = "10.18653/v1/2024.semeval-1.185",
pages = "1280--1287",
abstract = "ABSTRACT: This paper describes our approach to the SemEval-2024 safe biomedical Natural Language Inference for Clinical Trials (NLI4CT) task, which concerns classifying statements about Clinical Trial Reports (CTRs). We explored the capabilities of Mistral-7B, a generalistic open-source Large Language Model (LLM). We developed a prompt for the NLI4CT task, and fine-tuning a quantized version of the model using a slightly augmented version of the training dataset. The experimental results show that this approach can produce notable results in terms of the macro F1-score, while having limitations in terms of faithfulness and consistency. All the developed code is publicly available on a GitHub repository.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guimaraes-etal-2024-lisbon">
<titleInfo>
<title>Lisbon Computational Linguists at SemEval-2024 Task 2: Using a Mistral-7B Model and Data Augmentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Artur</namePart>
<namePart type="family">Guimarães</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bruno</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">João</namePart>
<namePart type="family">Magalhães</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>ABSTRACT: This paper describes our approach to the SemEval-2024 safe biomedical Natural Language Inference for Clinical Trials (NLI4CT) task, which concerns classifying statements about Clinical Trial Reports (CTRs). We explored the capabilities of Mistral-7B, a generalistic open-source Large Language Model (LLM). We developed a prompt for the NLI4CT task, and fine-tuning a quantized version of the model using a slightly augmented version of the training dataset. The experimental results show that this approach can produce notable results in terms of the macro F1-score, while having limitations in terms of faithfulness and consistency. All the developed code is publicly available on a GitHub repository.</abstract>
<identifier type="citekey">guimaraes-etal-2024-lisbon</identifier>
<identifier type="doi">10.18653/v1/2024.semeval-1.185</identifier>
<location>
<url>https://aclanthology.org/2024.semeval-1.185</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>1280</start>
<end>1287</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Lisbon Computational Linguists at SemEval-2024 Task 2: Using a Mistral-7B Model and Data Augmentation
%A Guimarães, Artur
%A Martins, Bruno
%A Magalhães, João
%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 guimaraes-etal-2024-lisbon
%X ABSTRACT: This paper describes our approach to the SemEval-2024 safe biomedical Natural Language Inference for Clinical Trials (NLI4CT) task, which concerns classifying statements about Clinical Trial Reports (CTRs). We explored the capabilities of Mistral-7B, a generalistic open-source Large Language Model (LLM). We developed a prompt for the NLI4CT task, and fine-tuning a quantized version of the model using a slightly augmented version of the training dataset. The experimental results show that this approach can produce notable results in terms of the macro F1-score, while having limitations in terms of faithfulness and consistency. All the developed code is publicly available on a GitHub repository.
%R 10.18653/v1/2024.semeval-1.185
%U https://aclanthology.org/2024.semeval-1.185
%U https://doi.org/10.18653/v1/2024.semeval-1.185
%P 1280-1287
Markdown (Informal)
[Lisbon Computational Linguists at SemEval-2024 Task 2: Using a Mistral-7B Model and Data Augmentation](https://aclanthology.org/2024.semeval-1.185) (Guimarães et al., SemEval 2024)
ACL