mlsanityData to 7 Oct 2026

TAP4LLM: Table Provider on Sampling, Augmenting, and Packing Semi-structured Data for Large Language Model Reasoning

arXiv 2312.09039 ↗First posted 14 Dec 2023cs.CL cs.AIcited by 32

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

Abstract (arXiv)

Table reasoning tasks have shown remarkable progress with the development of large language models (LLMs), which involve interpreting and drawing conclusions from tabular data based on natural language (NL) questions. Existing solutions mainly tested on smaller tables face scalability issues and struggle with complex queries due to incomplete or dispersed data across different table sections. To alleviate these challenges, we propose TAP4LLM as a versatile pre-processor suite for leveraging LLMs in table-based tasks effectively. It covers several distinct components: (1) table sampling to decompose large tables into manageable sub-tables based on query semantics, (2) table augmentation to enhance tables with additional knowledge from external sources or models, and (3) table packing & serialization to convert tables into various formats suitable for LLMs' understanding. In each module, we design and compare several common methods under various usage scenarios, aiming to shed light on the best practices for leveraging LLMs for table-reasoning tasks. Our experiments show that our method improves LLMs' reasoning capabilities in various tabular tasks and enhances the interaction between LLMs and tabular data by employing effective pre-processing.

Key facts. Cited by 32 papers in the map (data through 7 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 41 of its 79 references that are in the map. First posted on arXiv 14 Dec 2023.

Builds on

41 of 79 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning31 Jan
  2. 2022Large Language Models are few(1)-shot Table Reasoners13 Oct

Other references · 39

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2022Training language models to follow instructions with human feedbackcited by 15,712
  4. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  5. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  6. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  7. 2023Segment Anythingcited by 8,158
  8. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  9. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,464
  10. 2022Training Compute-Optimal Large Language Modelscited by 2,927
  11. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
  12. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
27 more
  1. 2022GLM-130B: An Open Bilingual Pre-trained Modelcited by 837
  2. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 786
  3. 2017Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learningcited by 679
  4. 2015Compositional Semantic Parsing on Semi-Structured Tablescited by 509
  5. 2023How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detectioncited by 472
  6. 2020TAPAS: Weakly Supervised Table Parsing via Pre-trainingcited by 432
  7. 2019TabFact: A Large-scale Dataset for Table-based Fact Verificationcited by 425
  8. 2020TaBERT: Pretraining for Joint Understanding of Textual and Tabular Datacited by 395
  9. 2020ToTTo: A Controlled Table-To-Text Generation Datasetcited by 267
  10. 2023AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Headcited by 264
  11. 2020HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Datacited by 263
  12. 2023MultiModal-GPT: A Vision and Language Model for Dialogue with Humanscited by 255
  13. 2021TAPEX: Table Pre-training via Learning a Neural SQL Executorcited by 233
  14. 2022UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Modelscited by 231
  15. 2022Binding Language Models in Symbolic Languagescited by 224
  16. 2021FEVEROUS: Fact Extraction and VERification Over Unstructured and Structured informationcited by 166
  17. 2020Detecting Hallucinated Content in Conditional Neural Sequence Generationcited by 151
  18. 2023ChatDB: Augmenting LLMs with Databases as Their Symbolic Memorycited by 136
  19. 2021TABBIE: Pretrained Representations of Tabular Datacited by 111
  20. 2020TUTA: Tree-based Transformers for Generally Structured Table Pre-trainingcited by 100
  21. 2023Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsingcited by 93
  22. 2021HTLM: Hyper-Text Pre-Training and Prompting of Language Modelscited by 58
  23. 2019E.T.-RNN: Applying Deep Learning to Credit Loan Applicationscited by 26
  24. 2023Generate, Transform, Answer: Question Specific Tool Synthesis for Tabular Datacited by 11
  25. 2022AnaMeta: A Table Understanding Dataset of Field Metadata Knowledge Shared by Multi-dimensional Data Analysis Taskscited by 8
  26. 2023Comparative Analysis of CHATGPT and the evolution of language modelscited by 6
  27. 2022Leveraging Data Recasting to Enhance Tabular Reasoningcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 16; 2025: 14; 2026: 2.

32 papers.

Sort:

By area:

  1. 2024Large Language Models Meet NLP: A Surveycited by 102
  2. 2024Synthesizing Text-to-SQL Data from Weak and Strong LLMscited by 53
  3. 2024Large Language Model for Table Processing: A Surveycited by 52
  4. 2024TableRAG: Million-Token Table Understanding with Language Modelscited by 40
  5. 2024A Survey of Table Reasoning with Large Language Modelscited by 29
  6. 2024LLM-Forest: Ensemble Learning of LLMs with Graph-Augmented Prompts for Data Imputationcited by 25
  7. 2025Large Language Models are Good Relational Learnerscited by 22
  8. 2025TableRAG: A Retrieval Augmented Generation Framework for Heterogeneous Document Reasoningcited by 22
  9. 2024Tree-of-Table: Unleashing the Power of LLMs for Enhanced Large-Scale Table Understandingcited by 20
  10. 2025TableMaster: A Recipe to Advance Table Understanding with Language Modelscited by 18
  11. 2025RAG over Tables: Hierarchical Memory Index, Multi-Stage Retrieval, and Benchmarkingcited by 17
  12. 2024PageRank Bandits for Link Predictioncited by 14
20 more
  1. 2024PromptIntern: Saving Inference Costs by Internalizing Recurrent Prompt during Large Language Model Fine-tuningcited by 13
  2. 2024TART: An Open-Source Tool-Augmented Framework for Explainable Table-based Reasoningcited by 10
  3. 2025Tabular Data Understanding with LLMs: A Survey of Recent Advances and Challengescited by 10
  4. 2024ALTER: Augmentation for Large-Table-Based Reasoningcited by 9
  5. 2025Sparks of Tabular Reasoning via Text2SQL Reinforcement Learningcited by 9
  6. 2024Table-LLM-Specialist: Language Model Specialists for Tables using Iterative Generator-Validator Fine-tuningcited by 7
  7. 2025TaTToo: Tool-Grounded Thinking PRM for Test-Time Scaling in Tabular Reasoningcited by 5
  8. 2024Vision Language Models for Spreadsheet Understanding: Challenges and Opportunitiescited by 4
  9. 2025Transformers Boost the Performance of Decision Trees on Tabular Data across Sample Sizescited by 4
  10. 2025TableLoRA: Low-rank Adaptation on Table Structure Understanding for Large Language Modelscited by 4
  11. 2025Chain-of-Query: Unleashing the Power of LLMs in SQL-Aided Table Understanding via Multi-Agent Collaborationcited by 4
  12. 2025Table Question Answering in the Era of Large Language Models: A Comprehensive Survey of Tasks, Methods, and Evaluationcited by 4
  13. 2024STEM-POM: Evaluating Language Models Math-Symbol Reasoning in Document Parsingcited by 3
  14. 2024RETQA: A Large-Scale Open-Domain Tabular Question Answering Dataset for Real Estate Sectorcited by 3
  15. 2025Tab-MIA: A Benchmark Dataset for Membership Inference Attacks on Tabular Data in LLMscited by 3
  16. 2024TREB: a BERT attempt for imputing tabular data imputationcited by 1
  17. 2025Large Language Models for Drug Overdose Prediction from Longitudinal Medical Recordscited by 0
  18. 2025Summarize-Exemplify-Reflect: Data-driven Insight Distillation Empowers LLMs for Few-shot Tabular Classificationcited by 0
  19. 2026FGTR: Fine-Grained Multi-Table Retrieval via Hierarchical LLM Reasoningcited by 0
  20. 2026CITBench: A Comprehensive Benchmark for Interactive Tabular Data Processing with LLMscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024TabSQLify: Enhancing Reasoning Capabilities of LLMs Through Table Decomposition
  2. 2025How well do LLMs reason over tabular data, really?
  3. 2025TReB: A Comprehensive Benchmark for Evaluating Table Reasoning Capabilities of Large Language Models
  4. 2025RUST-BENCH: Benchmarking LLM Reasoning on Unstructured Text within Structured Tables
  5. 2026ProgramTab: Boosting Table Reasoning of LLMs via Programmatic Paradigm
  6. 2023Rethinking Tabular Data Understanding with Large Language Models
  7. 2023Effective Distillation of Table-based Reasoning Ability from LLMs
  8. 2024OpenTab: Advancing Large Language Models as Open-domain Table Reasoners