mlsanityData to 7 Oct 2026

Piece of Table: A Divide-and-Conquer Approach for Selecting Subtables in Table Question Answering

arXiv 2412.07629 ↗First posted 10 Dec 2024cs.CL cs.AIcited by 3

Not on the map. Why?

Abstract (arXiv)

Applying language models (LMs) to tables is challenging due to the inherent structural differences between two-dimensional tables and one-dimensional text for which the LMs were originally designed. Furthermore, when applying linearized tables to LMs, the maximum token lengths often imposed in self-attention calculations make it difficult to comprehensively understand the context spread across large tables. To address these challenges, we present PieTa (Piece of Table), a new framework for subtable-based question answering (QA). PieTa operates through an iterative process of dividing tables into smaller windows, using LMs to select relevant cells within each window, and merging these cells into a subtable. This multi-resolution approach captures dependencies across multiple rows and columns while avoiding the limitations caused by long context inputs. Instantiated as a simple iterative subtable union algorithm, PieTa demonstrates improved performance over previous subtable-based QA approaches.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 33 of its 50 references that are in the map. First posted on arXiv 10 Dec 2024.

Builds on

33 of 50 references.

References · 33

  1. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  2. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  3. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  4. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  5. 2015Scheduled Sampling for Sequence Prediction with Recurrent Neural Networkscited by 779
  6. 2017Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learningcited by 679
  7. 2015Compositional Semantic Parsing on Semi-Structured Tablescited by 509
  8. 2020TAPAS: Weakly Supervised Table Parsing via Pre-trainingcited by 432
  9. 2021TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Financecited by 402
  10. 2020TaBERT: Pretraining for Joint Understanding of Textual and Tabular Datacited by 395
  11. 2023StructGPT: A General Framework for Large Language Model to Reason over Structured Datacited by 339
  12. 2020HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Datacited by 263
21 more
  1. 2021TAPEX: Table Pre-training via Learning a Neural SQL Executorcited by 233
  2. 2023LEVER: Learning to Verify Language-to-Code Generation with Executioncited by 228
  3. 2022Binding Language Models in Symbolic Languagescited by 224
  4. 2016Professor Forcing: A New Algorithm for Training Recurrent Networkscited by 214
  5. 2024Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understandingcited by 185
  6. 2023Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoningcited by 177
  7. 2021FeTaQA: Free-form Table Question Answeringcited by 174
  8. 2024The pitfalls of next-token predictioncited by 156
  9. 2024TableBench: A Comprehensive and Complex Benchmark for Table Question Answeringcited by 127
  10. 2022Large Language Models are few(1)-shot Table Reasonerscited by 116
  11. 2020TUTA: Tree-based Transformers for Generally Structured Table Pre-trainingcited by 100
  12. 2022TableFormer: Robust Transformer Modeling for Table-Text Encodingcited by 90
  13. 2023ReAcTable: Enhancing ReAct for Table Question Answeringcited by 76
  14. 2020On the Potential of Lexico-logical Alignments for Semantic Parsing to SQL Queriescited by 59
  15. 2024TabSQLify: Enhancing Reasoning Capabilities of LLMs Through Table Decompositioncited by 39
  16. 2023HYTREL: Hypergraph-enhanced Tabular Data Representation Learningcited by 35
  17. 2024Decomposition for Enhancing Attention: Improving LLM-based Text-to-SQL through Workflow Paradigmcited by 31
  18. 2024CABINET: Content Relevance based Noise Reduction for Table Question Answeringcited by 23
  19. 2024Tree-of-Table: Unleashing the Power of LLMs for Enhanced Large-Scale Table Understandingcited by 20
  20. 2021Multi-Row, Multi-Span Distant Supervision For Table+Text Questioncited by 12
  21. 2024Uncovering Limitations of Large Language Models in Information Seeking from Tablescited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025Table Question Answering in the Era of Large Language Models: A Comprehensive Survey of Tasks, Methods, and Evaluationcited by 4
  2. 2026FGTR: Fine-Grained Multi-Table Retrieval via Hierarchical LLM Reasoningcited by 0
  3. 2026PARTAB: Partition-Aware Reasoning with Structured Evidence for Scalable Table Understandingcited by 0