@inproceedings{bohacek-bravansky-2024-xgboost,
    title = "When {XGB}oost Outperforms {GPT}-4 on Text Classification: A Case Study",
    author = "Bohacek, Matyas  and
      Bravansky, Michal",
    editor = "Ovalle, Anaelia  and
      Chang, Kai-Wei  and
      Cao, Yang Trista  and
      Mehrabi, Ninareh  and
      Zhao, Jieyu  and
      Galstyan, Aram  and
      Dhamala, Jwala  and
      Kumar, Anoop  and
      Gupta, Rahul",
    booktitle = "Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.trustnlp-1.5/",
    doi = "10.18653/v1/2024.trustnlp-1.5",
    pages = "51--60",
    abstract = "Large language models (LLMs) are increasingly used for applications beyond text generation, ranging from text summarization to instruction following. One popular example of exploiting LLMs' zero- and few-shot capabilities is the task of text classification. This short paper compares two popular LLM-based classification pipelines (GPT-4 and LLAMA 2) to a popular pre-LLM-era classification pipeline on the task of news trustworthiness classification, focusing on performance, training, and deployment requirements. We find that, in this case, the pre-LLM-era ensemble pipeline outperforms the two popular LLM pipelines while being orders of magnitude smaller in parameter size."
}