Lisbon Computational Linguists at SemEval-2024 Task 2: Using A Mistral 7B Model and Data Augmentation

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Guimarães, Artur, Martins, Bruno, Magalhães, João
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916348402073600
author Guimarães, Artur
Martins, Bruno
Magalhães, João
author_facet Guimarães, Artur
Martins, Bruno
Magalhães, João
contents 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 generalist open-source Large Language Model (LLM). We developed a prompt for the NLI4CT task, and fine-tuned a quantized version of the model using an 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
format Preprint
id arxiv_https___arxiv_org_abs_2408_03127
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Lisbon Computational Linguists at SemEval-2024 Task 2: Using A Mistral 7B Model and Data Augmentation
Guimarães, Artur
Martins, Bruno
Magalhães, João
Computation and Language
I.2.7
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 generalist open-source Large Language Model (LLM). We developed a prompt for the NLI4CT task, and fine-tuned a quantized version of the model using an 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
title Lisbon Computational Linguists at SemEval-2024 Task 2: Using A Mistral 7B Model and Data Augmentation
topic Computation and Language
I.2.7
url https://arxiv.org/abs/2408.03127