@inproceedings{wu-etal-2026-table,
    title = "Table-R1: Region-based Reinforcement Learning for Table Understanding",
    author = "Wu, Zhenhe  and
      Yang, Jian  and
      He, Zhongjiang  and
      Pan, Changzai  and
      Liu, Jiaheng  and
      Wu, Xianjie  and
      Zhao, Yu  and
      Song, Shuangyong  and
      Li, Yongxiang  and
      Li, Zhoujun  and
      Li, Xuelong",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1364/",
    pages = "27374--27391",
    ISBN = "979-8-89176-395-1",
    abstract = "Tables present unique challenges for language models due to their structured row-column interactions, necessitating specialized approaches for effective comprehension. While large language models (LLMs) have demonstrated potential in table reasoning through prompting and techniques like chain-of-thought (CoT) and program-of-thought (PoT), optimizing their performance for table question answering remains underexplored. In this paper, we introduce region-based Table-R1, a novel reinforcement learning approach that enhances LLM table understanding by integrating region evidence into reasoning steps. Our method employs Region-Enhanced Supervised Fine-Tuning (RE-SFT) to guide models in identifying relevant table regions before generating answers, incorporating textual, symbolic, and program-based reasoning. Additionally, Table-Aware Group Relative Policy Optimization (TARPO) introduces a mixed reward system to dynamically balance region accuracy and answer correctness, with decaying region rewards and consistency penalties to align reasoning steps. Experiments show that Table-R1 achieves an average performance improvement of 14.36 points across multiple base models on three benchmark datasets, even outperforming baseline models with ten times the number of parameters, while TARPO significantly reduces the reasoning token consumption by 67.5{\%} compared to GRPO, significantly advancing LLM capabilities in efficient tabular reasoning."
}