mlsanityData to 13 Oct 2026

Large Language Models are Complex Table Parsers

arXiv 2312.11521 ↗First posted 13 Dec 2023cs.CL cs.AIcited by 28

Not on the map. Why?

Abstract (arXiv)

With the Generative Pre-trained Transformer 3.5 (GPT-3.5) exhibiting remarkable reasoning and comprehension abilities in Natural Language Processing (NLP), most Question Answering (QA) research has primarily centered around general QA tasks based on GPT, neglecting the specific challenges posed by Complex Table QA. In this paper, we propose to incorporate GPT-3.5 to address such challenges, in which complex tables are reconstructed into tuples and specific prompt designs are employed for dialogues. Specifically, we encode each cell's hierarchical structure, position information, and content as a tuple. By enhancing the prompt template with an explanatory description of the meaning of each tuple and the logical reasoning process of the task, we effectively improve the hierarchical structure awareness capability of GPT-3.5 to better parse the complex tables. Extensive experiments and results on Complex Table QA datasets, i.e., the open-domain dataset HiTAB and the aviation domain dataset AIT-QA show that our approach significantly outperforms previous work on both datasets, leading to state-of-the-art (SOTA) performance.

Key facts. Cited by 28 papers in the map (data through 13 Oct 2026). Builds on 30 of its 41 references that are in the map. First posted on arXiv 13 Dec 2023.

Builds on

30 of 41 references.

References · 30

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,304
  2. 2020Language Models are Few-Shot Learnerscited by 32,320
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,549
  4. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,322
  5. 2022Large Language Models are Zero-Shot Reasonerscited by 4,348
  6. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,133
  7. 2023A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivitycited by 894
  8. 2017Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learningcited by 687
  9. 2015Compositional Semantic Parsing on Semi-Structured Tablescited by 513
  10. 2020TAPAS: Weakly Supervised Table Parsing via Pre-trainingcited by 433
  11. 2020TaBERT: Pretraining for Joint Understanding of Textual and Tabular Datacited by 397
  12. 2020HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Datacited by 264
18 more
  1. 2023Self-collaboration Code Generation via ChatGPTcited by 257
  2. 2023Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4cited by 202
  3. 2021FeTaQA: Free-form Table Question Answeringcited by 175
  4. 2022Large Language Models are few(1)-shot Table Reasonerscited by 116
  5. 2022TableFormer: Robust Transformer Modeling for Table-Text Encodingcited by 91
  6. 2018TypeSQL: Knowledge-based Type-Aware Neural Text-to-SQL Generationcited by 81
  7. 2023Is ChatGPT a Good Causal Reasoner? A Comprehensive Evaluationcited by 69
  8. 2018Memory Augmented Policy Optimization for Program Synthesis and Semantic Parsingcited by 57
  9. 2021MATE: Multi-view Attention for Table Transformer Efficiencycited by 54
  10. 2021AIT-QA: Question Answering Dataset over Complex Tables in the Airline Industrycited by 44
  11. 2022Table Pre-training: A Survey on Model Architectures, Pre-training Objectives, and Downstream Taskscited by 42
  12. 2022A Survey on Table Question Answering: Recent Advancescited by 41
  13. 2023Will Affective Computing Emerge from Foundation Models and General AI? A First Evaluation on ChatGPTcited by 41
  14. 2023Empower Large Language Model to Perform Better on Industrial Domain-Specific Question Answeringcited by 41
  15. 2021Capturing Row and Column Semantics in Transformer Based Question Answering over Tablescited by 31
  16. 2023How to Design Translation Prompts for ChatGPT: An Empirical Studycited by 31
  17. 2023A Preliminary Evaluation of ChatGPT for Zero-shot Dialogue Understandingcited by 31
  18. 2023Improving ChatGPT Prompt for Code Generationcited by 28

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2024: 16; 2025: 6; 2026: 6.

28 papers.

Sort:

By area:

  1. 2024Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Surveycited by 158
  2. 2024TableBench: A Comprehensive and Complex Benchmark for Table Question Answeringcited by 128
  3. 2024TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarioscited by 76
  4. 2024Large Language Model for Table Processing: A Surveycited by 52
  5. 2024A Survey of Table Reasoning with Large Language Modelscited by 29
  6. 2024DOPRA: Decoding Over-accumulation Penalization and Re-allocation in Specific Weighting Layercited by 27
  7. 2024GraphOTTER: Evolving LLM-based Graph Reasoning for Complex Table Question Answeringcited by 18
  8. 2024Distilling Instruction-following Abilities of Large Language Models with Task-aware Curriculum Planningcited by 13
  9. 2024Efficient Prompting for LLM-based Generative Internet of Thingscited by 12
  10. 2025RealHiTBench: A Comprehensive Realistic Hierarchical Table Benchmark for Evaluating LLM-Based Table Analysiscited by 12
  11. 2024When Raw Data Prevails: Are Large Language Model Embeddings Effective in Numerical Data Representation for Medical Machine Learning Applications?cited by 11
  12. 2025RoT: Enhancing Table Reasoning with Iterative Row-Wise Traversalscited by 10
16 more
  1. 2025Table-r1: Self-supervised and Reinforcement Learning for Program-based Table Reasoning in Small Language Modelscited by 7
  2. 2024HiQA: A Hierarchical Contextual Augmentation RAG for Multi-Documents QAcited by 6
  3. 2025Table Question Answering in the Era of Large Language Models: A Comprehensive Survey of Tasks, Methods, and Evaluationcited by 5
  4. 2024CT2C-QA: Multimodal Question Answering over Chinese Text, Table and Chartcited by 4
  5. 2024Seek and Solve Reasoning for Table Question Answeringcited by 3
  6. 2025Cooking Up Creativity: Enhancing LLM Creativity through Structured Recombinationcited by 3
  7. 2025Improving Table Understanding with LLMs and Entity-Oriented Searchcited by 3
  8. 2024Through the Thicket: A Study of Number-Oriented LLMs derived from Random Forest Modelscited by 2
  9. 2024HySem: A context length optimized LLM pipeline for unstructured tabular extractioncited by 1
  10. 2026Orthogonal Hierarchical Decomposition for Structure-Aware Table Understanding with Large Language Modelscited by 1
  11. 2024Knowledge in Triples for LLMs: Enhancing Table QA Accuracy with Semantic Extractioncited by 0
  12. 2026QUIETT: Query-Independent Table Transformation for Robust Reasoningcited by 0
  13. 2026Replacing Multi-Step Assembly of Data Preparation Pipelines with One-Step LLM Pipeline Generation for Table QAcited by 0
  14. 2026LIT-RAGBench: Benchmarking Generator Capabilities of Large Language Models in Retrieval-Augmented Generationcited by 0
  15. 2026DataFactory: Collaborative Multi-Agent Framework for Advanced Table Question Answeringcited by 0
  16. 2026How to Utilize Complementary Vision-Text Information for 2D Structure Understandingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Efficient Table QA via TableGrid Navigation and Progressive Inference Prompting
  2. 2025M3TQA: Massively Multilingual Multitask Table Question Answering
  3. 2021HiTab: A Hierarchical Table Dataset for Question Answering and Natural Language Generation
  4. 2025Improving Table Retrieval with Question Generation from Partial Tables
  5. 2023Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning
  6. 2026ASTRA: Adaptive Semantic Tree Reasoning Architecture for Complex Table Question Answering
  7. 2022ProQA: Structural Prompt-based Pre-training for Unified Question Answering
  8. 2024TANQ: An open domain dataset of table answered questions