@inproceedings{ho-etal-2025-firefly,
    title = "Firefly Team at {S}em{E}val-2025 Task 8: Question-Answering over Tabular Data using {SQL}/Python generation with Closed-Source Large Language Models",
    author = "Ho, Nga  and
      Ho, Tuyen  and
      Le, Hung  and
      Thin, Dang",
    editor = "Rosenthal, Sara  and
      Ros{\'a}, Aiala  and
      Ghosh, Debanjan  and
      Zampieri, Marcos",
    booktitle = "Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/transition-to-people-yaml/2025.semeval-1.136/",
    pages = "1028--1033",
    ISBN = "979-8-89176-273-2",
    abstract = "In this paper, we describe our official system of the Firefly team for two main tasks in the SemEval-2025 Task 8: Question-Answering over Tabular Data. Our solution employs large language models (LLMs) to translate natural language queries into executable code, specifically Python and SQL, which are then used to generate answers categorized into five predefined types. Our empirical evaluation highlights the superiority of Python code generation over SQL for this challenge. Besides, the experimental results show that our system has achieved competitive performance in two subtasks. In Subtask I: Databench QA, where we rank the Top 9 across datasets of any size. Besides, our solution achieved competitive results and ranked 5th place in Subtask II: Databench QA Lite, where datasets are restricted to a maximum of 20 rows."
}