TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarios
Not on the map. Why?
Cited by 21 in LLM reasoning, but placed by its own abstract, which didn’t fit.
Abstract (arXiv)
We introduce TableLLM, a robust large language model (LLM) with 8 billion parameters, purpose-built for proficiently handling tabular data manipulation tasks, whether they are embedded within documents or spreadsheets, catering to real-world office scenarios. We propose a distant supervision method for training, which comprises a reasoning process extension strategy, aiding in training LLMs to understand reasoning patterns more effectively as well as a cross-way validation strategy, ensuring the quality of the automatically generated data. To evaluate the performance of TableLLM, we have crafted benchmarks tailored to address both document and spreadsheet formats as well as constructed a well-organized evaluation pipeline capable of handling both scenarios. Thorough evaluations underscore the advantages of TableLLM when compared to various existing general-purpose and tabular data-focused LLMs. We have publicly released the model checkpoint, source code, benchmarks, and a web application for user interaction. Our codes and data are publicly available at https://github.com/TableLLM/TableLLM.
Key facts. Cited by 76 papers in the map (data through 7 Oct 2026). Builds on 35 of its 59 references that are in the map. First posted on arXiv 28 Mar 2024.
Builds on
35 of 59 references.
References · 35
- 2022Training language models to follow instructions with human feedbackcited by 15,712
- 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
- 2023Code Llama: Open Foundation Models for Codecited by 2,105
- 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
- 2017Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learningcited by 679
- 2015Compositional Semantic Parsing on Semi-Structured Tablescited by 509
- 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 465
- 2020TAPAS: Weakly Supervised Table Parsing via Pre-trainingcited by 432
- 2021TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Financecited by 402
- 2020TaBERT: Pretraining for Joint Understanding of Textual and Tabular Datacited by 395
- 2023StructGPT: A General Framework for Large Language Model to Reason over Structured Datacited by 339
- 2021TAPEX: Table Pre-training via Learning a Neural SQL Executorcited by 233
23 more
- 2022UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Modelscited by 231
- 2022Binding Language Models in Symbolic Languagescited by 224
- 2024Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understandingcited by 185
- 2023Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoningcited by 177
- 2021FeTaQA: Free-form Table Question Answeringcited by 174
- 2020GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsingcited by 171
- 2020Open Question Answering over Tables and Textcited by 163
- 2023C3: Zero-shot Text-to-SQL with ChatGPTcited by 159
- 2023ChatDB: Augmenting LLMs with Databases as Their Symbolic Memorycited by 136
- 2023TableLlama: Towards Open Large Generalist Models for Tablescited by 136
- 2024InfiAgent-DABench: Evaluating Agents on Data Analysis Taskscited by 134
- 2021TABBIE: Pretrained Representations of Tabular Datacited by 111
- 2022TableFormer: Robust Transformer Modeling for Table-Text Encodingcited by 90
- 2023Data-Copilot: Bridging Billions of Data and Humans with Autonomous Workflowcited by 76
- 2023ReAcTable: Enhancing ReAct for Table Question Answeringcited by 76
- 2023Table-GPT: Table-tuned GPT for Diverse Table Taskscited by 69
- 2021MATE: Multi-view Attention for Table Transformer Efficiencycited by 54
- 2021GitTables: A Large-Scale Corpus of Relational Tablescited by 44
- 2022Table Pre-training: A Survey on Model Architectures, Pre-training Objectives, and Downstream Taskscited by 42
- 2023Large Language Models are Complex Table Parserscited by 28
- 2023DB-GPT: Empowering Database Interactions with Private Large Language Modelscited by 27
- 2024TAT-LLM: A Specialized Language Model for Discrete Reasoning over Tabular and Textual Datacited by 19
- 2023Localize, Retrieve and Fuse: A Generalized Framework for Free-Form Question Answering over Tablescited by 6
Built on by
Citing papers per year: 2024: 15; 2025: 41; 2026: 20.
76 papers.
Sort:
By area:
- 2024LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitaskscited by 367
- 2024TableBench: A Comprehensive and Complex Benchmark for Table Question Answeringcited by 127
- 2024A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discoverycited by 96
- 2024TableGPT2: A Large Multimodal Model with Tabular Data Integrationcited by 69
- 2025Eagle 2: Building Post-Training Data Strategies from Scratch for Frontier Vision-Language Modelscited by 69
- 2025DeepAnalyze: Agentic Large Language Models for Autonomous Data Sciencecited by 49
- 2025A Survey on Personalized Alignment -- The Missing Piece for Large Language Models in Real-World Applicationscited by 40
- 2025Table-R1: Region-based Reinforcement Learning for Table Understandingcited by 35
- 2025Table-R1: Inference-Time Scaling for Table Reasoningcited by 23
- 2026LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decodingcited by 20
- 2025Reasoning-Table: Exploring Reinforcement Learning for Table Reasoningcited by 18
- 2024SpreadsheetLLM: Encoding Spreadsheets for Large Language Modelscited by 15
38 more
- 2024StrucText-Eval: Evaluating Large Language Model's Reasoning Ability in Structure-Rich Textcited by 13
- 2024Efficient Multi-Agent Collaboration with Tool Use for Online Planning in Complex Table Question Answeringcited by 13
- 2024Auto-Formula: Recommend Formulas in Spreadsheets using Contrastive Learning for Table Representationscited by 12
- 2025ST-Raptor: LLM-Powered Semi-Structured Table Question Answeringcited by 11
- 2025Rethinking Table Instruction Tuningcited by 10
- 2025RoT: Enhancing Table Reasoning with Iterative Row-Wise Traversalscited by 10
- 2024FLEXTAF: Enhancing Table Reasoning with Flexible Tabular Formatscited by 8
- 2024Large Language Models Engineer Too Many Simple Features For Tabular Datacited by 8
- 2025NeedleInATable: Exploring Long-Context Capability of Large Language Models towards Long-Structured Tablescited by 8
- 2025Atomic Reasoning for Scientific Table Claim Verificationcited by 8
- 2025Zephyrus: An Agentic Framework for Weather Sciencecited by 8
- 2025LocateAnything3D: Vision-Language 3D Detection with Chain-of-Sightcited by 8
- 2025CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesiscited by 7
- 2025General Table Question Answering via Answer-Formula Joint Generationcited by 7
- 2025Plugging Schema Graph into Multi-Table QA: A Human-Guided Framework for Reducing LLM Reliancecited by 7
- 2024GoNoGo: An Efficient LLM-based Multi-Agent System for Streamlining Automotive Software Release Decision-Makingcited by 6
- 2025Efficient numeracy in language models through single-token number embeddingscited by 6
- 2025Mixture-of-Minds: Multi-Agent Reinforcement Learning for Table Understandingcited by 6
- 2025TabularMath: Understanding Math Reasoning over Tables with Large Language Modelscited by 5
- 2025TabDSR: Decompose, Sanitize, and Reason for Complex Numerical Reasoning in Tabular Datacited by 5
- 2025TableLoRA: Low-rank Adaptation on Table Structure Understanding for Large Language Modelscited by 4
- 2025TableDreamer: Progressive and Weakness-guided Data Synthesis from Scratch for Table Instruction Tuningcited by 4
- 2025Table Question Answering in the Era of Large Language Models: A Comprehensive Survey of Tasks, Methods, and Evaluationcited by 4
- 2026TabSieve: Explicit In-Table Evidence Selection for Tabular Predictioncited by 4
- 2026FinSheet-Bench: From Simple Lookups to Complex Reasoning, Where LLMs Break on Financial Spreadsheetscited by 4
- 2025Formula-R1: Incentivizing LLM Reasoning over Complex Tables with Numerical Computation via Formula-Driven Reinforcement Learningcited by 3
- 2025TableZoomer: A Collaborative Agent Framework for Large-scale Table Question Answeringcited by 3
- 2025Same Content, Different Representations: A Controlled Study for Table QAcited by 3
- 2025STaR: Towards Effective and Stable Table Reasoning via Slow-Thinking Large Language Modelscited by 3
- 20242D-TPE: Two-Dimensional Positional Encoding Enhances Table Understanding for Large Language Modelscited by 2
- 2025What Really Matters for Table LLMs? A Meta-Evaluation of Model and Data Effectscited by 2
- 2025AraTable: Benchmarking LLMs' Reasoning and Understanding of Arabic Tabular Datacited by 2
- 2026DTBench: A Synthetic Benchmark for Document-to-Table Extractioncited by 2
- 2026DocSage: An Information Structuring Agent for Multi-Doc Multi-Entity Question Answeringcited by 2
- 2024HySem: A context length optimized LLM pipeline for unstructured tabular extractioncited by 1
- 2024Talking with Tables for Better LLM Factual Data Interactionscited by 1
- 2025HCT-QA: A Benchmark for Question Answering on Human-Centric Tablescited by 1
- 2025p2-TQA: A Process-based Preference Learning Framework for Self-Improving Table Question Answering Modelscited by 1
50 most cited of 76 All 76 (JSON)
- 2026DeepTable: Structural Attention Biases and Tree Path Encoding for Hierarchical Table Understanding7 Sep 2026
- 2026When LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing Errors30 Jun 2026
- 2026CITBench: A Comprehensive Benchmark for Interactive Tabular Data Processing with LLMs29 Jun 2026
- 2026TabClaw: An Interactive and Self-Evolving Agent for Spreadsheet Manipulation and Table Reasoning9 Jun 2026
- 2026TABVERSE: Benchmarking Cross-Format Table Understanding in LLMs and VLMs8 Jun 2026
- 2026BlueFin: Benchmarking LLM Agents on Financial Spreadsheets29 May 2026
- 2026LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding26 May 2026
- 2026Efficient Table QA via TableGrid Navigation and Progressive Inference Prompting18 May 2026
- 2026The Power of Order: Fooling LLMs with Adversarial Table Permutations1 May 2026
- 2026A Closer Look into LLMs for Table Understanding16 Mar 2026
- 2026DocSage: An Information Structuring Agent for Multi-Doc Multi-Entity Question Answering12 Mar 2026
- 2026TableMind++: An Uncertainty-Aware Programmatic Agent for Tool-Augmented Table Reasoning8 Mar 2026
38 more
- 2026FinSheet-Bench: From Simple Lookups to Complex Reasoning, Where LLMs Break on Financial Spreadsheets7 Mar 2026
- 2026DTBench: A Synthetic Benchmark for Document-to-Table Extraction14 Feb 2026
- 2026TabSieve: Explicit In-Table Evidence Selection for Tabular Prediction12 Feb 2026
- 2026ST-Raptor: An Agentic System for Semi-Structured Table QA3 Feb 2026
- 2026Orthogonal Hierarchical Decomposition for Structure-Aware Table Understanding with Large Language Models2 Feb 2026
- 2026GLEAN: Grounded Lightweight Evaluation Anchors for Contamination-Aware Tabular Reasoning22 Jan 2026
- 2026ReasonTabQA: A Comprehensive Benchmark for Table Question Answering from Real World Industrial Scenarios12 Jan 2026
- 2026An Empirical Investigation of Robustness in Large Language Models under Tabular Distortions8 Jan 2026
- 2025Debugging Tabular Log as Dynamic Graphs28 Dec 2025
- 2025Fairness Is Not Just Ethical: Performance Trade-Off via Data Correlation Tuning to Mitigate Bias in ML Software19 Dec 2025
- 2025JT-DA: Enhancing Data Analysis with Tool-Integrated Table Reasoning Large Language Models7 Dec 2025
- 2025Instruction Tuning of Large Language Models for Tabular Data Generation-in One Day28 Nov 2025
- 2025LocateAnything3D: Vision-Language 3D Detection with Chain-of-Sight25 Nov 2025
- 2025Lost in the Pipeline: How Well Do Large Language Models Handle Data Preparation?17 Nov 2025
- 2025STaR: Towards Effective and Stable Table Reasoning via Slow-Thinking Large Language Models14 Nov 2025
- 2025TabDSR: Decompose, Sanitize, and Reason for Complex Numerical Reasoning in Tabular Data4 Nov 2025
- 2025Mixture-of-Minds: Multi-Agent Reinforcement Learning for Table Understanding23 Oct 2025
- 2025DeepAnalyze: Agentic Large Language Models for Autonomous Data Science19 Oct 2025
- 2025Table Question Answering in the Era of Large Language Models: A Comprehensive Survey of Tasks, Methods, and Evaluation8 Oct 2025
- 2025Efficient numeracy in language models through single-token number embeddings8 Oct 2025
- 2025Zephyrus: An Agentic Framework for Weather Science5 Oct 2025
- 2025Same Content, Different Representations: A Controlled Study for Table QA26 Sep 2025
- 2025DeKeyNLU: Enhancing Natural Language to SQL Generation through Task Decomposition and Keyword Extraction18 Sep 2025
- 2025TableZoomer: A Collaborative Agent Framework for Large-scale Table Question Answering1 Sep 2025
- 2025Summarize-Exemplify-Reflect: Data-driven Insight Distillation Empowers LLMs for Few-shot Tabular Classification29 Aug 2025
- 2025ST-Raptor: LLM-Powered Semi-Structured Table Question Answering25 Aug 2025
- 2025Innovative tokenisation of structured data for LLM training3 Aug 2025
- 2025AraTable: Benchmarking LLMs' Reasoning and Understanding of Arabic Tabular Data24 Jul 2025
- 2025Schema-R1: A reasoning training approach for schema linking in Text-to-SQL Task13 Jun 2025
- 2025TableDreamer: Progressive and Weakness-guided Data Synthesis from Scratch for Table Instruction Tuning10 Jun 2025
- 2025Atomic Reasoning for Scientific Table Claim Verification8 Jun 2025
- 2025Plugging Schema Graph into Multi-Table QA: A Human-Guided Framework for Reducing LLM Reliance4 Jun 2025
- 2025Reasoning-Table: Exploring Reinforcement Learning for Table Reasoning2 Jun 2025
- 2025Formula-R1: Incentivizing LLM Reasoning over Complex Tables with Numerical Computation via Formula-Driven Reinforcement Learning29 May 2025
- 2025Table-R1: Inference-Time Scaling for Table Reasoning29 May 2025
- 2025RelationalFactQA: A Benchmark for Evaluating Tabular Fact Retrieval from Large Language Models27 May 2025
- 2025TabularMath: Understanding Math Reasoning over Tables with Large Language Models26 May 2025
- 2025p2-TQA: A Process-based Preference Learning Framework for Self-Improving Table Question Answering Models23 May 2025
50 newest of 76 All 76 (JSON)
- 2024LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitaskscited by 367
- 2025Table-R1: Region-based Reinforcement Learning for Table Understandingcited by 35
- 2025Table-R1: Inference-Time Scaling for Table Reasoningcited by 23
- 2025Reasoning-Table: Exploring Reinforcement Learning for Table Reasoningcited by 18
- 2024StrucText-Eval: Evaluating Large Language Model's Reasoning Ability in Structure-Rich Textcited by 13
- 2025Rethinking Table Instruction Tuningcited by 10
- 2025RoT: Enhancing Table Reasoning with Iterative Row-Wise Traversalscited by 10
- 2024FLEXTAF: Enhancing Table Reasoning with Flexible Tabular Formatscited by 8
- 2025Atomic Reasoning for Scientific Table Claim Verificationcited by 8
- 2025CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesiscited by 7
- 2025TabularMath: Understanding Math Reasoning over Tables with Large Language Modelscited by 5
- 2025TabDSR: Decompose, Sanitize, and Reason for Complex Numerical Reasoning in Tabular Datacited by 5
12 most cited of 21 All 21 (JSON)
- 2026TabClaw: An Interactive and Self-Evolving Agent for Spreadsheet Manipulation and Table Reasoning9 Jun 2026
- 2026TableMind++: An Uncertainty-Aware Programmatic Agent for Tool-Augmented Table Reasoning8 Mar 2026
- 2026FinSheet-Bench: From Simple Lookups to Complex Reasoning, Where LLMs Break on Financial Spreadsheets7 Mar 2026
- 2026Orthogonal Hierarchical Decomposition for Structure-Aware Table Understanding with Large Language Models2 Feb 2026
- 2026ReasonTabQA: A Comprehensive Benchmark for Table Question Answering from Real World Industrial Scenarios12 Jan 2026
- 2025JT-DA: Enhancing Data Analysis with Tool-Integrated Table Reasoning Large Language Models7 Dec 2025
- 2025STaR: Towards Effective and Stable Table Reasoning via Slow-Thinking Large Language Models14 Nov 2025
- 2025TabDSR: Decompose, Sanitize, and Reason for Complex Numerical Reasoning in Tabular Data4 Nov 2025
- 2025AraTable: Benchmarking LLMs' Reasoning and Understanding of Arabic Tabular Data24 Jul 2025
- 2025Atomic Reasoning for Scientific Table Claim Verification8 Jun 2025
- 2025Reasoning-Table: Exploring Reinforcement Learning for Table Reasoning2 Jun 2025
- 2025Formula-R1: Incentivizing LLM Reasoning over Complex Tables with Numerical Computation via Formula-Driven Reinforcement Learning29 May 2025
12 newest of 21 All 21 (JSON)
- 2025DeepAnalyze: Agentic Large Language Models for Autonomous Data Sciencecited by 49
- 2024Efficient Multi-Agent Collaboration with Tool Use for Online Planning in Complex Table Question Answeringcited by 13
- 2025Zephyrus: An Agentic Framework for Weather Sciencecited by 8
- 2024GoNoGo: An Efficient LLM-based Multi-Agent System for Streamlining Automotive Software Release Decision-Makingcited by 6
- 2025Mixture-of-Minds: Multi-Agent Reinforcement Learning for Table Understandingcited by 6
- 2025TableZoomer: A Collaborative Agent Framework for Large-scale Table Question Answeringcited by 3
- 2026ST-Raptor: An Agentic System for Semi-Structured Table QAcited by 1
- 2026BlueFin: Benchmarking LLM Agents on Financial Spreadsheetscited by 1
- 2026BlueFin: Benchmarking LLM Agents on Financial Spreadsheets29 May 2026
- 2026ST-Raptor: An Agentic System for Semi-Structured Table QA3 Feb 2026
- 2025Mixture-of-Minds: Multi-Agent Reinforcement Learning for Table Understanding23 Oct 2025
- 2025DeepAnalyze: Agentic Large Language Models for Autonomous Data Science19 Oct 2025
- 2025Zephyrus: An Agentic Framework for Weather Science5 Oct 2025
- 2025TableZoomer: A Collaborative Agent Framework for Large-scale Table Question Answering1 Sep 2025
- 2024Efficient Multi-Agent Collaboration with Tool Use for Online Planning in Complex Table Question Answering28 Dec 2024
- 2024GoNoGo: An Efficient LLM-based Multi-Agent System for Streamlining Automotive Software Release Decision-Making19 Aug 2024
- 2024TableGPT2: A Large Multimodal Model with Tabular Data Integrationcited by 69
- 2025Eagle 2: Building Post-Training Data Strategies from Scratch for Frontier Vision-Language Modelscited by 69
- 2026LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decodingcited by 20
- 2026TABVERSE: Benchmarking Cross-Format Table Understanding in LLMs and VLMscited by 1
- 2026TABVERSE: Benchmarking Cross-Format Table Understanding in LLMs and VLMs8 Jun 2026
- 2026LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding26 May 2026
- 2025Eagle 2: Building Post-Training Data Strategies from Scratch for Frontier Vision-Language Models20 Jan 2025
- 2024TableGPT2: A Large Multimodal Model with Tabular Data Integration4 Nov 2024
- 2026A Closer Look into LLMs for Table Understandingcited by 0
- 2026A Closer Look into LLMs for Table Understanding16 Mar 2026
- 2024TableBench: A Comprehensive and Complex Benchmark for Table Question Answeringcited by 127
- 2024A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discoverycited by 96
- 2024SpreadsheetLLM: Encoding Spreadsheets for Large Language Modelscited by 15
- 2024Auto-Formula: Recommend Formulas in Spreadsheets using Contrastive Learning for Table Representationscited by 12
- 2025ST-Raptor: LLM-Powered Semi-Structured Table Question Answeringcited by 11
- 2024Large Language Models Engineer Too Many Simple Features For Tabular Datacited by 8
- 2025NeedleInATable: Exploring Long-Context Capability of Large Language Models towards Long-Structured Tablescited by 8
- 2025LocateAnything3D: Vision-Language 3D Detection with Chain-of-Sightcited by 8
- 2025General Table Question Answering via Answer-Formula Joint Generationcited by 7
- 2025Plugging Schema Graph into Multi-Table QA: A Human-Guided Framework for Reducing LLM Reliancecited by 7
- 2025Efficient numeracy in language models through single-token number embeddingscited by 6
- 2025TableLoRA: Low-rank Adaptation on Table Structure Understanding for Large Language Modelscited by 4
12 most cited of 38 All 38 (JSON)
- 2026DeepTable: Structural Attention Biases and Tree Path Encoding for Hierarchical Table Understanding7 Sep 2026
- 2026When LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing Errors30 Jun 2026
- 2026CITBench: A Comprehensive Benchmark for Interactive Tabular Data Processing with LLMs29 Jun 2026
- 2026Efficient Table QA via TableGrid Navigation and Progressive Inference Prompting18 May 2026
- 2026The Power of Order: Fooling LLMs with Adversarial Table Permutations1 May 2026
- 2026DTBench: A Synthetic Benchmark for Document-to-Table Extraction14 Feb 2026
- 2026TabSieve: Explicit In-Table Evidence Selection for Tabular Prediction12 Feb 2026
- 2026GLEAN: Grounded Lightweight Evaluation Anchors for Contamination-Aware Tabular Reasoning22 Jan 2026
- 2026An Empirical Investigation of Robustness in Large Language Models under Tabular Distortions8 Jan 2026
- 2025Debugging Tabular Log as Dynamic Graphs28 Dec 2025
- 2025Fairness Is Not Just Ethical: Performance Trade-Off via Data Correlation Tuning to Mitigate Bias in ML Software19 Dec 2025
- 2025Instruction Tuning of Large Language Models for Tabular Data Generation-in One Day28 Nov 2025
12 newest of 38 All 38 (JSON)
Similar, not cited
Close in wording, no citation either way
- 2025RealHiTBench: A Comprehensive Realistic Hierarchical Table Benchmark for Evaluating LLM-Based Table Analysis
- 2025Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding
- 2026ProgramTab: Boosting Table Reasoning of LLMs via Programmatic Paradigm
- 2024Large Language Model for Table Processing: A Survey
- 2025Tabular Data Understanding with LLMs: A Survey of Recent Advances and Challenges
- 2025How well do LLMs reason over tabular data, really?
- 2023TAP4LLM: Table Provider on Sampling, Augmenting, and Packing Semi-structured Data for Large Language Model Reasoning
- 2023Rethinking Tabular Data Understanding with Large Language Models