@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://preview.aclanthology.org/fix-sig-urls/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."
}