@inproceedings{yao-etal-2025-111dut,
    title = "111{DUT} at {S}em{E}val-2025 Task 8:Hierarchical Chain-of-Thought Reasoning and Multi-Model Deliberation for Robust {T}able{QA}",
    author = "Yao, Jiaqi  and
      Yu, Erchen  and
      Tian, Yicen  and
      Kang, Yiyang  and
      Zhang, Jiayi  and
      Lin, Hongfei  and
      Zong, Linlin  and
      Xu, Bo",
    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/corrections-2025-08/2025.semeval-1.32/",
    pages = "216--221",
    ISBN = "979-8-89176-273-2",
    abstract = "The proliferation of structured tabular data in domains like healthcare and finance has intensified the demand for precise table question answering, particularly for complex numerical reasoning and cross-domain generalization. Existing approaches struggle with implicit semantics and multi-step arithmetic operations. This paper presents our solution for SemEval-2025 task,including three synergistic components: (1) a Schema Profiler that extracts structural metadata via LLM-driven analysis and statistical validation, (2) a Hierarchical Chain-of-Thought module that decomposes questions into four stages(semantic anchoring, schema mapping, query synthesis, and self-correction)to ensure SQL validity, and (3) a Confidence-Accuracy Voting mechanism that resolves discrepancies across LLMs through weighted ensemble decisions. Our framework achieves scores of 81.23 on Databench and 81.99 on Databench{\_}lite, ranking 6th and 5th respectively, demonstrating the effectiveness of structured metadata guidance and cross-model deliberation in complex TableQA scenarios."
}