@inproceedings{jiang-etal-2025-tabdsr,
    title = "{T}ab{DSR}: Decompose, Sanitize, and Reason for Complex Numerical Reasoning in Tabular Data",
    author = "Jiang, Changjiang  and
      Yu, Fengchang  and
      Chen, Haihua  and
      Lu, Wei  and
      Zeng, Jin",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/name-variant-enfa-fane/2025.findings-emnlp.169/",
    doi = "10.18653/v1/2025.findings-emnlp.169",
    pages = "3172--3196",
    ISBN = "979-8-89176-335-7",
    abstract = "Complex reasoning over tabular data is crucial in real-world data analysis, yet large language models (LLMs) often underperform due to complex queries, noisy data, and limited numerical capabilities. To address these issues, we propose TabDSR, a three-agent framework consisting of: (1) a query decomposer that breaks down complex questions, (2) a table sanitizer that cleans and filters noisy tables, and (3) a program-of-thoughts (PoT)-based reasoner that generates executable code to derive the final answer from the sanitized table. To ensure unbiased evaluation and mitigate data leakage, we introduce a new dataset, CalTab151, specifically designed for complex numerical reasoning over tables. Experimental results demonstrate that TabDSR consistently outperforms existing methods, achieving state-of-the-art (SOTA) performance with 8.79{\%}, 6.08{\%}, and 19.87{\%} accuracy improvement on TAT-QA, TableBench, and CalTab151, respectively. Moreover, our framework integrates seamlessly with mainstream LLMs, providing a robust solution for complex tabular numerical reasoning. These findings highlight the effectiveness of our framework in enhancing LLM performance for complex tabular numerical reasoning."
}