@inproceedings{site-etal-2025-itunlp,
    title = "{ITUNLP} at {S}em{E}val-2025 Task 8: Question-Answering over Tabular Data: A Zero-Shot Approach using {LLM}-Driven Code Generation",
    author = {Site, Atakan  and
      Erdemir, Emre  and
      Eryi{\u{g}}it, G{\"u}l{\c{s}}en},
    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-1.198/",
    pages = "1504--1514",
    ISBN = "979-8-89176-273-2",
    abstract = "This paper presents our system for SemEval-2025 Task 8: DataBench, Question-Answeringover Tabular Data. The primary objective ofthis task is to perform question answering ongiven tabular datasets from diverse domains;under two subtasks: DataBench QA (SubtaskI) and DataBench Lite QA (Subtask II). Totackle both subtasks, we developed a zero-shotsolution with a particular emphasis on lever-aging Large Language Model (LLM)-basedcode generation. Specifically, we proposeda Python code generation framework, utiliz-ing state-of-the-art open-source LLMs to gen-erate executable Pandas code via optimizedprompting strategies. Our experiments revealthat different LLMs exhibit varying levels ofeffectiveness in Python code generation. Addi-tionaly, results show that Python code genera-tion achieves superior performance in tabularquestion answering compared to alternative ap-proaches. Although our ranking among zero-shot systems is unknown at the time of this pa-per{'}s submission, our system achieved eighthplace in Subtask I and sixth place in Subtask IIamong the 30 systems that outperformed thebaseline in the open-source models category."
}