@inproceedings{bujnowski-etal-2025-samsung,
    title = "{S}amsung Research {P}oland at {S}em{E}val-2025 Task 8: {LLM} ensemble methods for {QA} over tabular data",
    author = "Bujnowski, Pawel  and
      Dryjanski, Tomasz  and
      Goltz, Christian  and
      Swiderski, Bartosz  and
      Paszkiewicz, Natalia  and
      Kuzma, Bartlomiej  and
      Rutkowski, Jacek  and
      Stepka, Jakub  and
      Dudek, Milosz  and
      Siemiatkowski, Wojciech  and
      Plichta, Weronika  and
      Paziewski, Bart{\l}omiej  and
      Grabowski, Maciej  and
      Beksa, Katarzyna  and
      Bordzicka, Zuzanna  and
      Ostrowski, Filip  and
      Sochacki, Grzegorz",
    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-1.163/",
    pages = "1223--1232",
    ISBN = "979-8-89176-273-2",
    abstract = "Question answering using Large Language Models has gained significant popularity inboth everyday communication and at the workplace. However, certain tasks, such as querying tables, still pose challenges for commercial and open-source chatbots powered by advanceddeep learning models. Addressing these challenges requires specialized approaches.During the SemEval-2025 Task 8 competition focused on tabular data, our solution achieved86.21{\%} accuracy and took 2nd place out of 100 teams. In this paper we present ten methodsthat significantly improve the baseline solution. Our code is available as open-source."
}