# STable: Table Generation Framework for Encoder-Decoder Models

arXiv: https://arxiv.org/abs/2206.04045 · HTML: https://mlsanity.com/paper/2206.04045/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 35 references that are in the map.
- First posted on arXiv 8 Jun 2022.

## Builds on (most cited first, 25 of 25)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [UnifiedQA: Crossing Format Boundaries With a Single QA System](https://mlsanity.com/paper/2005.00700/) (2020)
- [LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding](https://mlsanity.com/paper/2012.14740/) (2020)
- [Image-based table recognition: data, model, and evaluation](https://mlsanity.com/paper/1911.10683/) (2019)
- [The Natural Language Decathlon: Multitask Learning as Question Answering](https://mlsanity.com/paper/1806.08730/) (2018)
- [Challenges in Data-to-Document Generation](https://mlsanity.com/paper/1707.08052/) (2017)
- [Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer](https://mlsanity.com/paper/2102.09550/) (2021)
- [Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extraction](https://mlsanity.com/paper/2106.09232/) (2021)
- [Insertion Transformer: Flexible Sequence Generation via Insertion Operations](https://mlsanity.com/paper/1902.03249/) (2019)
- [Ask Me Anything: Dynamic Memory Networks for Natural Language Processing](https://mlsanity.com/paper/1506.07285/) (2015)
- [LAMBERT: Layout-Aware (Language) Modeling for information extraction](https://mlsanity.com/paper/2002.08087/) (2020)
- [AxCell: Automatic Extraction of Results from Machine Learning Papers](https://mlsanity.com/paper/2004.14356/) (2020)
- [Text-to-Table: A New Way of Information Extraction](https://mlsanity.com/paper/2109.02707/) (2021)
- [Robust (Controlled) Table-to-Text Generation with Structure-Aware Equivariance Learning](https://mlsanity.com/paper/2205.03972/) (2022)
- [DWIE: an entity-centric dataset for multi-task document-level information extraction](https://mlsanity.com/paper/2009.12626/) (2020)
- [Self-Attention with Structural Position Representations](https://mlsanity.com/paper/1909.00383/) (2019)
- [Representations for Question Answering from Documents with Tables and Text](https://mlsanity.com/paper/2101.10573/) (2021)
- [Beyond Error Propagation in Neural Machine Translation: Characteristics of Language Also Matter](https://mlsanity.com/paper/1809.00120/) (2018)
- [A New Approach to Overgenerating and Scoring Abstractive Summaries](https://mlsanity.com/paper/2104.01726/) (2021)
- [Injecting Knowledge Base Information into End-to-End Joint Entity and Relation Extraction and Coreference Resolution](https://mlsanity.com/paper/2107.02286/) (2021)
- [From Dataset Recycling to Multi-Property Extraction and Beyond](https://mlsanity.com/paper/2011.03228/) (2020)
- [Doc2Dict: Information Extraction as Text Generation](https://mlsanity.com/paper/2105.07510/) (2021)

## Built on by (most cited first, 15 of 15)

- [Document Understanding Dataset and Evaluation (DUDE)](https://mlsanity.com/paper/2305.08455/) (2023)
- [Struc-Bench: Are Large Language Models Really Good at Generating Complex Structured Data?](https://mlsanity.com/paper/2309.08963/) (2023)
- [gTBLS: Generating Tables from Text by Conditional Question Answering](https://mlsanity.com/paper/2403.14457/) (2024)
- [Testing the Limits of Unified Sequence to Sequence LLM Pretraining on Diverse Table Data Tasks](https://mlsanity.com/paper/2310.00789/) (2023)
- [Structsum Generation for Faster Text Comprehension](https://mlsanity.com/paper/2401.06837/) (2024)
- [DocTabQA: Answering Questions from Long Documents Using Tables](https://mlsanity.com/paper/2408.11490/) (2024)
- [Map&Make: Schema Guided Text to Table Generation](https://mlsanity.com/paper/2505.23174/) (2025)
- [Scaling Experiments in Self-Supervised Cross-Table Representation Learning](https://mlsanity.com/paper/2309.17339/) (2023)
- [iTBLS: A Dataset of Interactive Conversations Over Tabular Information](https://mlsanity.com/paper/2404.12580/) (2024)
- [Structuring the Unstructured: A Systematic Review of Text-to-Structure Generation for Agentic AI with a Universal Evaluation Framework](https://mlsanity.com/paper/2508.12257/) (2025)
- [Towards Multi-Modal DBMSs for Seamless Querying of Texts and Tables](https://mlsanity.com/paper/2304.13559/) (2023)
- [CT-Eval: Benchmarking Chinese Text-to-Table Performance in Large Language Models](https://mlsanity.com/paper/2405.12174/) (2024)
- [Beyond Isolated Dots: Benchmarking Structured Table Construction as Deep Knowledge Extraction](https://mlsanity.com/paper/2507.16271/) (2025)
- [Moneyball with LLMs: Analyzing Tabular Summarization in Sports Narratives](https://mlsanity.com/paper/2510.18173/) (2025)
- [TEAR: Table Extraction with Attribute Recommendation from Texts via Large Language Models](https://mlsanity.com/paper/2609.15205/) (2026)

## Abstract (arXiv)

The output structure of database-like tables, consisting of values structured in horizontal rows and vertical columns identifiable by name, can cover a wide range of NLP tasks. Following this constatation, we propose a framework for text-to-table neural models applicable to problems such as extraction of line items, joint entity and relation extraction, or knowledge base population. The permutation-based decoder of our proposal is a generalized sequential method that comprehends information from all cells in the table. The training maximizes the expected log-likelihood for a table's content across all random permutations of the factorization order. During the content inference, we exploit the model's ability to generate cells in any order by searching over possible orderings to maximize the model's confidence and avoid substantial error accumulation, which other sequential models are prone to. Experiments demonstrate a high practical value of the framework, which establishes state-of-the-art results on several challenging datasets, outperforming previous solutions by up to 15%.