Table QA

QA: Question Answering

Table question answering asks how systems can answer natural-language questions over tables, spreadsheets, relational databases, and tables embedded in documents or images. Common approaches preserve structure with trees, graphs, or cell-level evidence; retrieve relevant regions; and combine language models with SQL or Python execution, sometimes through multi-agent planning. Benchmarks test lookup, aggregation, numerical reasoning, multi-hop questions, and visual or cross-modal understanding, and show persistent weaknesses on complex calculations and real-world tables. A central tension is that flexible language-model reasoning can be difficult to verify and sensitive to table format, while symbolic execution is more auditable but depends on accurate structure extraction and query translation.

Latest papers

66 papers9 papers in the last four weeks, level with the four weeks before. 0.1% of all new papers.

HARP-LoRA: Hierarchy-Conditioned Rank Projection for Low-Rank Adaptation in Scientific Table Understanding
Oct 25, 2026Hossein Sholehrasa, Mohammadhossein Amini, Doina Caragea +8Low-Rank Adaptation Table QA
1DATA Consortium and FARAD Program, Kansas State University, Olathe, KS, USA · Department of Computer Science, Kansas State University, Manhattan, KS, USA · Olin Business School, Washington University in St. Louis, St. Louis, Missouri, USA +5
Benchmark for Structured Retrieval-Augmented Generation in Perovskite Photovoltaics
Oct 18, 2026Qiwei Han, Chi Zhou, Gaoxiang YuanStructured RAG RAG Evaluation
Department of Chemistry, Duke University, Durham, NC 27708, USA · Department of Computer Science, Georgia Institute of Technology, Atlanta, GA 30332, USA · Department of Electrical and Computer Engineering, Tandon School of Engineering, New York University, Brooklyn, NY 11201, USA
RDL-Bench: A Benchmark for Task-Aware Question Answering over Relational Databases
Oct 15, 2026Yao Cheng, Siqiang LuoTable QA Relational Databases
College of Computing and Data Science, Nanyang Technological University, Singapore
Fan Out or Relay? Ownership-Aware Routing for LLM Agents Querying Siloed Tables
Oct 13, 2026Zhexi FengLLM Agent Routing Table QA
Department of Electrical and Computer Engineering, University of California San Diego, La Jolla, CA 92093, USA
MERIT: Multimodal Evidence Reasoning over Image Tables
Oct 13, 2026Haoyang Jiang, Zhuotong Fan, Mingyang Yi +3Table QA Automated Fact-Checking
Renmin University of China · Independent Researcher · Beike Inc.
Understanding Errors in LLM-Based Question Answering over Imperfect Tables
Oct 3, 2026Baowen Zhang, Wei Fan, Ruman Wang +1Table QA Language Model Error Detection
University of Wisconsin–Madison · University of Auckland, Auckland, New Zealand · Liaoning Provincial People’s Hospital +1
VIGIL: Verifier-Informed Gated Improvement Loop for Spreadsheet Question Answering
Oct 3, 2026Kang Li, Lu He, Sandarsita GuntupalliTable QA Continual Learning for LLM Agents
Atlassian · Carnegie Mellon University
Answering clinicians' questions over trial evidence tables with verifiable, feedback-driven language models
Oct 1, 2026Manan Roy Choudhury, Suparno Roy Chowdhury, Swastik Sahoo +5Clinical QA Table QA
Arizona State University, Tempe, Arizona, USA · Mayo Clinic, Phoenix, Arizona, USA
TRACE: Target-Aware Retrieval, Attributed Evidence, and Contract-Constrained Extraction for LitTraceQA
Sep 30, 2026Sachin Gupta, Divya GodaraScientific QA Evidence Retrieval
Independent Researcher San Jose, USA
InterTab: Interleaved Visual-Structure Alignment for Multi-Modal Table Reasoning
Sep 26, 2026Hanqian Li, Sirui Huang, Chen Ling +12Table QA Multimodal CoT Reasoning
The Hong Kong University of Science and Technology (Guangzhou) · Ant Group · Hong Kong Polytechnic University +4
From Tables to Quantified Statements: Evaluating LLM Inference Generation through Executable Verification
Sep 21, 2026Mai Mohamed Eida, Gunjan Anand, Ayush Singh +1Table QA LLM Evaluation
University of Illinois Urbana Champaign
Q&A on Any Spreadsheet Requires Interpreting Its Grid Structure
Sep 17, 2026Zofia SmoleńDocument Chunking Table QA
Systems Research Institute, Polish Academy of Sciences Warsaw, Poland
Tables Decoded: DELTA for Structure, TARQA for Understanding
Sep 15, 2026Jahanvi Rajput, Dhruv Kudale, Saikiran Kasturi +2Table QA Table Structure Recognition
Indian Institute of Technology Bombay · IIT Bombay · BharatGen
DeepTable: Structural Attention Biases and Tree Path Encoding for Hierarchical Table Understanding
Sep 7, 2026Jyun-Ying Yen, Cheng-Kuan Lin, Yu-Chee TsengTable QA Table Structure Recognition
Department of Computer Science National Yang Ming Chiao Tung University, Taiwan
Open Tabular Insight Extraction: Where Do We Stand, and Where Should We Go?
Sep 7, 2026Daniel Gomm, Maarten de Rijke, Madelon HulsebosTable QA
Centrum Wiskunde & Informatica · University of Amsterdam
STQA: A Benchmark for Stock-Focused Tabular Question Answering over Historical and Forecasted Data
Sep 5, 2026Baoxu An, Wenmian Yang, Zhensheng Wang +1Table QA Time Series QA
School of Artificial Intelligence, Beijing Normal University, Beijing, PR China · Institute of Artificial Intelligence and Future Networks, Beijing Normal University, Zhuhai, PR China · Beijing Normal-Hong Kong Baptist University, Zhuhai, PR China
TabScope: Question-Adaptive Scope Selection for Table Question Answering
Sep 3, 2026Yuxiang Wang, Junhao Gan, Jianzhong QiTable QA
The University of Melbourne
H2Table: Hierarchical Hypergraph-Enhanced Large Language Models for Complex Table Reasoning
Sep 1, 2026Jia Ling, Yangfan Wang, Chen Tang +4Table QA Hierarchical Representation Learning
Harbin Institute of Technology · AI Research Center, Midea Group (Shanghai) Co., Ltd. · Changchun University of Science and Technology +1
A Table Is Worth 64 Tokens: Pixel-level Compression for Multi-Table Document Question Answering
Aug 27, 2026Iñigo Alonso, Mirella LapataDocument QA Visual Token Compression
School of Informatics University of Edinburgh Edinburgh, UK
TabuLM: Morphology-Aware Tabular Pre-training for Low-Resource Languages
Aug 27, 2026Ireddi Rakshitha, Devavarapu Yashwanth, Ntakirutimana PierreLanguage Model Pretraining Language Modeling
Barclays · Carnegie Mellon University
PARTAB: Partition-Aware Reasoning with Structured Evidence for Scalable Table Understanding
Aug 25, 2026Md Mahadi Hasan Nahid, Davood RafieiTable Reasoning Table QA
University of Alberta
EKLAV: Elicited Key CoT Learning via Answer only superVision
Jul 28, 2026Adarsh Singh, Aman Singh, Kushal Raj Bhandari +3Table QA CoT Distillation
Arizona State University · Rensselaer Polytechnic Institute · Scale AI
Semantically Similar, Yet Not Answerable: Diagnosing the Semantic-Answerability Gap in Table RAG
Jul 20, 2026Jiaming Tian, Liyao Li, Wentao Ye +6Table QA Retrieval-Augmented Generation
Zhejiang University · Bank of Hangzhou Co., Ltd. · Zhejiang Lab
Gold-Guided Programmatic Distillation for Financial Reasoning over Hybrid Tables and Text
Jul 16, 2026Yun Dong, Erica Zhao, Elana ChenTable QA Financial QA
College of Computing · Georgia Institute of Technology · Department of Management Science & Engineering +2
Data Analysis in the Wild: Benchmarking Large Language Models Against Real-World Data Complexities
Jul 7, 2026So Hasegawa, Shailaja Keyur Sampat, Lei Liu +1Table QA LLM Evaluation
Fujitsu Research of America, Santa Clara CA 95054, USA
Latent Bridges for Multi-Table Question Answering
Jun 27, 2026Simone Varriale, Tamara Cucumides, Floris Geerts +1Table QA LLM Grounding
EURECOM · University of Antwerp
Evolving from Lessons: Skill-Augmented Table Graph Reasoning for Operation-wise Table Question Answering
Jun 20, 2026Guixin Su, Qiankun Pi, Mayi Xu +5Table QA
School of Computer Science, Wuhan University, Wuhan, China
MoCA-Agent: A Market-of-Claims Code Agent for Financial and Numerical Reasoning
Jun 10, 2026Abdelrahman Abdallah, AbdelRahim A. Elmadany, Sameh Al Natour +3Table QA LLM Answer Verification
University of Innsbruck · University of British Columbia · λCanada Research Chair in NLP and ML +1
TABVERSE: Benchmarking Cross-Format Table Understanding in LLMs and VLMs
Jun 8, 2026Momina Ahsan, Sarfraz Ahmad, Ming Shan Hee +2Document Understanding Table QA
1Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) · 2Singapore University of Technology and Design (SUTD)
CRAFT: A Unified Counterfactual Reasoning Framework for Tabular Question Answering and Fact Verification
Jun 5, 2026Chenshuo Pan, Yu Zhao, Jie Zhang +7Table QA Claim Verification
Xingchen AGI Lab,China Telecom Artificial Intelligence Technology (Beijing) Co., Ltd

Oct 25, 2026J/K move · Enter open · S save

HARP-LoRA: Hierarchy-Conditioned Rank Projection for Low-Rank Adaptation in Scientific Table Understanding

Hossein Sholehrasa, Mohammadhossein Amini, Doina Caragea, Remya Ampadi Ramachandran+7

1DATA Consortium and FARAD Program, Kansas State University, Olathe, KS, USA · Department of Computer Science, Kansas State University, Manhattan, KS, USA · Olin Business School, Washington University in St. Louis, St. Louis, Missouri, USA+5

Low-Rank Adaptation Table QA

Open paper AskPDF arXiv

Tabular data is widely used in scientific applications, where complex layouts, including multi-level headers, merged cells, captions, and footnotes, make information extraction difficult. This is particularly important in pharmacokinetics (PK), where values must be correctly associated with the drug, species, dose, administration route, unit, and experimental condition. Parameter-efficient fine-tuning methods such as Low-Rank Adaptation (LoRA) reduce adaptation cost but do not explicitly incorporate relationships between table values and surrounding headers. We introduce HARP-LoRA, a hierarchy-conditioned rank projection method for low-rank adaptation in scientific table understanding. HARP-LoRA extends projected LoRA by constructing token-specific intrinsic representations from the row- and column-header hierarchies of each data token. These representations condition the low-rank down-projection, incorporating hierarchical context while keeping the pretrained model and random projection tensors frozen. We evaluate HARP-LoRA on 950 manually annotated PK tables from 587 scientific articles and on WikiTableQuestions (WikiTQ) using Llama~~3.2 3B, Llama~~3.1 8B, and Gemma~~3 27B. With Llama~~3.1 8B, HARP-LoRA achieves a PK F1-score of 57.64% and WikiTQ accuracy of 53.15%, improving over LoRA by 1.42 and 6.56 points, respectively. With Gemma~3 27B, it achieves the best PK F1-score of 70.63% and WikiTQ accuracy of 56.87%. These results use only 172K, 197K, and 547K trainable parameters, far fewer than LoRA and TableLoRA. Overall, conditioning lightweight adapters on table-header hierarchies improves extraction from scientific tables and reasoning over flatter general-domain tables while maintaining parameter efficiency. Code is available at: https://github.com/hosseinsholehrasa/HARP-LoRA