@inproceedings{aktas-etal-2026-birdturk,
    title = "{BIRDT}urk: Adaptation of the {BIRD} Text-to-{SQL} Dataset to {T}urkish",
    author = {Akta{\c{s}}, Burak  and
      Baytekin, Mehmet Can  and
      K{\"o}se, S{\"u}ha Ka{\u{g}}an  and
      {\.I}lbilgi, {\"O}mer  and
      Y{\i}lmaz, Elif {\"O}zge  and
      Toraman, Cagri  and
      G{\"o}r{\"u}r, Bilge Kaan},
    editor = {Oflazer, Kemal  and
      K{\"o}ksal, Abdullatif  and
      Varol, Onur},
    booktitle = "Proceedings of the Second Workshop Natural Language Processing for {T}urkic Languages ({SIGTURK} 2026)",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/manual-author-scripts/2026.sigturk-1.13/",
    pages = "155--171",
    ISBN = "979-8-89176-370-8",
    abstract = "Text-to-SQL systems have achieved strong performance on English benchmarks, yet their behavior in morphologically rich, low-resource languages remains largely unexplored. We introduce BIRDTurk, the first Turkish adaptation of the BIRD benchmark, constructed through a controlled translation pipeline that adapts schema identifiers to Turkish while strictly preserving the logical structure and execution semantics of SQL queries and databases. Translation quality is validated on a sample size determined by the Central Limit Theorem to ensure 95{\%} confidence, achieving 98.15{\%} accuracy on human-evaluated samples. Using BIRDTurk, we evaluate inference-based prompting, agentic multi-stage reasoning, and supervised fine-tuning. Our results reveal that Turkish introduces consistent performance degradation{--}driven by both structural linguistic divergence and underrepresentation in LLM pretraining{--}while agentic reasoning demonstrates stronger cross-lingual robustness. Supervised fine-tuning remains challenging for standard multilingual baselines but scales effectively with modern instruction-tuned models. BIRDTurk provides a controlled testbed for cross-lingual Text-to-SQL evaluation under realistic database conditions. We release the training and development splits to support future research."
}