Orthogonal Hierarchical Decomposition for Structure-Aware Table Understanding with Large Language Models
Zhejiang University of Technology, China（浙江工业大学，中国）；Zhejiang Key Laboratory of Visual Information Intelligent Processing, China（浙江视觉信息智能处理重点实验室，中国）；University of Aberdeen, UK（爱丁堡大学，英国）
Bin Cao, Huixian Lu, Chenwen Ma, Ting Wang, Ruizhe Li, Jing Fan
Complex tables with multi-level headers, merged cells and heterogeneous layouts pose persistent challenges for LLMs in both understanding and reasoning. Existing approaches typically rely on table linearization or normalized grid modeling. However, these representations struggle to explicitly capture hierarchical structures and cross-dimensional dependencies, which can lead to misalignment between structural semantics and textual representations for non-standard tables. To address this issue, we propose an Orthogonal Hierarchical Decomposition (OHD) framework that constructs structure-preserving input representations of complex tables for LLMs. OHD introduces an Orthogonal Tree Induction (OTI) method based on spatial--semantic co-constraints, which decomposes irregular tables into a column tree and a row tree to capture vertical and horizontal hierarchical dependencies, respectively. Building on this representation, we design a dual-pathway association protocol to symmetrically reconstruct semantic lineage of each cell, and incorporate an LLM as a semantic arbitrator to align multi-level semantic information. We evaluate OHD framework on two complex table question answering benchmarks, AITQA and HiTab. Experimental results show that OHD consistently outperforms existing representation paradigms across multiple evaluation metrics.
School of Computer Science（计算机学院）；Fudan University（复旦大学）；Academy for Engineering Technology（工程技术研究院）；Shanghai Children’s Hospital of Fudan University（复旦大学附属儿科医院）；National Children’s Medical Center（国家儿童医学中心）
Tree-of-Table: Unleashing the Power of LLMs for Enhanced Large-Scale Table Understanding
University of Science and Technology of China（中国科学技术大学）；Alibaba Group（阿里巴巴集团）；Singapore University of Technology and Design（新加坡科技设计大学）；Shanghai Jiao Tong University（上海交通大学）
DocParser: Hierarchical Structure Parsing of Document Renderings
ETH Zurich（苏黎世联邦理工学院）
翻译渲染（e. G. PDF、扫描）转换为分层文档结构，这在许多实际应用程序的日常工作中有着广泛的需求。然而，一个整体的，原则性的方法来推断完整的层次结构的文件是失踪。作为补救措施，我们开发了“DocParser”：一个端到端的系统，用于解析完整的文档结构-包括所有文本元素，嵌套的图形，表格和表格单元格结构。我们的第二个贡献是提供了一个数据集，用于评估分层文档结构解析。我们的第三个贡献是提出了一个可扩展的学习框架设置特定领域的数据是稀缺的，我们解决了一种新的方法，以弱监督，显着提高了文档结构解析性能。我们的实验证实了我们提出的弱监督的有效性：与没有弱监督的基线相比，它将检测文档实体的平均精度提高了39.1%，将分类层次关系的F1得分提高了35.8%。
TableEval: A Real-World Benchmark for Complex, Multilingual, and Multi-Structured Table Question Answering
Beijing Wenge Technology Co., Ltd.（北京文格科技有限公司）；State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, CAS, Beijing, China（多模态人工智能系统国家重点实验室，自动化研究所，中国，北京）；School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences, China（中国科学院大学advanced interdisciplinary sciences学院，中国）
