While Large Language Models (LLMs) are increasingly deployed for table-related tasks, the internal mechanisms enabling them to process linearized two-dimensional structured tables remain opaque. In this work, we investigate the process of table understanding by dissecting the atomic task of cell location. Through activation patching and complementary interpretability techniques, we delineate the table understanding mechanism into a sequential three-stage pipeline: Semantic Binding, Coordinate Localization, and Information Extraction. We demonstrate that models locate the target cell via an ordinal mechanism that counts discrete delimiters to resolve coordinates. Furthermore, column indices are encoded within a linear subspace that allows for precise steering of model focus through vector arithmetic. Finally, we reveal that models generalize to multi-cell location tasks by multiplexing the identical attention heads identified during atomic location. Our findings provide a comprehensive explanation of table understanding within Transformer architectures.
TableLoRA: Low-rank Adaptation on Table Structure Understanding for Large Language Models
State Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University（人机混合增强智能国家重点实验室，人工智能与机器人研究院，西安交通大学）；Peking University（北京大学）；Microsoft（微软公司）
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）
Table Understanding and (Multimodal) LLMs: A Cross-Domain Case Study on Scientific vs. Non-Scientific Data
Deutsches Forschungszentrum für Künstliche Intelligenz GmbH (DFKI)（德国人工智能研究中心有限公司）；Technische Universität Berlin（柏林技术大学）；BIFOLD；Deutsche Telekom（德国电信）；Common Crawl Foundation（Common Crawl基金会）；Humboldt-Universität zu Berlin（柏林洪堡大学）
HIPPO: Enhancing the Table Understanding Capability of LLMs through Hybrid-Modal Preference Optimization
School of Computer Science and Engineering, Northeastern University, Shenyang, China（东北大学计算机科学与工程学院）；Department of Computer Science and Technology, Tsinghua University, Beijing, China（清华大学计算机科学与技术系）；Huawei Technologies Co., Ltd（华为技术有限公司）
Tracking the Feature Dynamics in LLM Training: A Mechanistic Study
Department of Computer Science（计算机科学系）；Rutgers University（罗格斯大学）；Section for Health Data Science and AI（健康数据科学与人工智能部门）；University of Copenhagen（哥本哈根大学）
Bridge the Gap between Language models and Tabular Understanding
Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Hong Kong University of Science and Technology（香港科技大学）；Microsoft（微软）；Duke University（杜克大学）；Yale University（耶鲁大学）；Peking University（北京大学）
2D-TPE: Two-Dimensional Positional Encoding Enhances Table Understanding for Large Language Models
Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学高瓴人工智能学院）；Ant Group（蚂蚁集团）；Kunming University of Science and Technology（昆明理工大学）
Towards Table-to-Text Generation with Pretrained Language Model: A Table Structure Understanding and Text Deliberating Approach
University of Science and Technology of China（中国科学技术大学）；Baidu Research（百度研究院）；Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Guangzhou HKUST Fok Ying Tung Research Institute（广州香港科技大学霍英东研究院）
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；Baidu Inc（百度公司）；School of Artificial Intelligence, Beijing Normal University（北京师范大学人工智能学院）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）
Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neurons
Department of Computer Science and Technology, BNRist（计算机科学与技术系，BNRist）；Shenzhen International Graduate School（深圳国际研究生院）；KIRC, Institute for Artificial Intelligence, Tsinghua University（人工智能研究院，清华大学）
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络安全学院）
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）
TabularMath: Understanding Math Reasoning over Tables with Large Language Models
National Key Laboratory for Novel Software Technology, Nanjing University（南京大学新型软件技术国家重点实验室）；School of Artificial Intelligence, Nanjing University（南京大学人工智能学院）；School of Intelligence Science and Technology, Nanjing University（南京大学智能科学与技术学院）
Benchmarking Multimodal LLMs on Recognition and Understanding over Chemical Tables
State Key Laboratory of Cognitive Intelligence（认知智能国家重点实验室）；University of Science and Technology of China（中国科学技术大学）；Artificial Intelligence Research Institute（人工智能研究院）；iFLYTEK Co., Ltd（iFLYTEK公司）
TableTime: Reformulating Time Series Classification as Training-Free Table Understanding with Large Language Models
State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China（认知智能国家重点实验室，中国科学技术大学）；Artificial Intelligence Research Institute, iFLYTEK Co., Ltd（人工智能研究院，iFLYTEK公司）
