@inproceedings{aguiar-etal-2024-seme,
    title = "{SEME} at {S}em{E}val-2024 Task 2: Comparing Masked and Generative Language Models on Natural Language Inference for Clinical Trials",
    author = "Aguiar, Mathilde  and
      Zweigenbaum, Pierre  and
      Naderi, Nona",
    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-1.143/",
    doi = "10.18653/v1/2024.semeval-1.143",
    pages = "986--996",
    abstract = "This paper describes our submission to Task 2 of SemEval-2024: Safe Biomedical Natural Language Inference for Clinical Trials. The Multi-evidence Natural Language Inference for Clinical Trial Data (NLI4CT) consists of a Textual Entailment (TE) task focused on the evaluation of the consistency and faithfulness of Natural Language Inference (NLI) models applied to Clinical Trial Reports (CTR). We test 2 distinct approaches, one based on finetuning and ensembling Masked Language Models and the other based on prompting Large Language Models using templates, in particular, using Chain-Of-Thought and Contrastive Chain-Of-Thought. Prompting Flan-T5-large in a 2-shot setting leads to our best system that achieves 0.57 F1 score, 0.64 Faithfulness, and 0.56 Consistency."
}