@inproceedings{liu-thoma-2024-fzi,
    title = "{FZI}-{WIM} at {S}em{E}val-2024 Task 2: Self-Consistent {C}o{T} for Complex {NLI} in Biomedical Domain",
    author = "Liu, Jin  and
      Thoma, Steffen",
    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-1.184/",
    doi = "10.18653/v1/2024.semeval-1.184",
    pages = "1269--1279",
    abstract = "This paper describes the inference system of FZI-WIM at the SemEval-2024 Task 2: Safe Biomedical Natural Language Inference for Clinical Trials. Our system utilizes the chain of thought (CoT) paradigm to tackle this complex reasoning problem and further improve the CoT performance with self-consistency. Instead of greedy decoding, we sample multiple reasoning chains with the same prompt and make thefinal verification with majority voting. The self-consistent CoT system achieves a baseline F1 score of 0.80 (1st), faithfulness score of 0.90 (3rd), and consistency score of 0.73 (12th). We release the code and data publicly."
}