Pith. sign in

REVIEW 9 cited by

TAPEX: Table Pre-training via Learning a Neural SQL Executor

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2107.07653 v3 pith:B4QR64LJ submitted 2021-07-16 cs.CL cs.AI

Qian Liu , Bei Chen , Jiaqi Guo , Morteza Ziyadi , Zeqi Lin , Weizhu Chen , Jian-Guang Lou This is my paper
classification cs.CLcs.AI
keywords pre-trainingtapexaccuracydatatabledenotationexecutorlarge-scale
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recent progress in language model pre-training has achieved a great success via leveraging large-scale unstructured textual data. However, it is still a challenge to apply pre-training on structured tabular data due to the absence of large-scale high-quality tabular data. In this paper, we propose TAPEX to show that table pre-training can be achieved by learning a neural SQL executor over a synthetic corpus, which is obtained by automatically synthesizing executable SQL queries and their execution outputs. TAPEX addresses the data scarcity challenge via guiding the language model to mimic a SQL executor on the diverse, large-scale and high-quality synthetic corpus. We evaluate TAPEX on four benchmark datasets. Experimental results demonstrate that TAPEX outperforms previous table pre-training approaches by a large margin and achieves new state-of-the-art results on all of them. This includes the improvements on the weakly-supervised WikiSQL denotation accuracy to 89.5% (+2.3%), the WikiTableQuestions denotation accuracy to 57.5% (+4.8%), the SQA denotation accuracy to 74.5% (+3.5%), and the TabFact accuracy to 84.2% (+3.2%). To our knowledge, this is the first work to exploit table pre-training via synthetic executable programs and to achieve new state-of-the-art results on various downstream tasks. Our code can be found at https://github.com/microsoft/Table-Pretraining.

Discussion (0). Sign in to comment.

Forward citations

Cited by 9 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. SpreadsheetBench 2: Evaluating Agents on End-to-End Business Spreadsheet Workflows

    cs.SE 2026-06 unverdicted novelty 7.0 of 10

    SpreadsheetBench 2 provides 321 expert-validated tasks from authentic business data showing frontier LLMs reach only 34.89% overall accuracy on end-to-end spreadsheet workflows.

  2. RSAT: Structured Attribution Makes Small Language Models Faithful Table Reasoners

    cs.CL 2026-04 unverdicted novelty 7.0 of 10

    RSAT makes 1-8B language models produce faithful table reasoning by training them to output structured steps with cell citations, using SFT followed by GRPO with an NLI-based faithfulness reward.

  3. RSAT: Structured Attribution Makes Small Language Models Faithful Table Reasoners

    cs.CL 2026-04 conditional novelty 7.0 of 10

    RSAT uses SFT on verified traces followed by GRPO with NLI faithfulness rewards to make 1-8B models produce verifiable table reasoning with cell citations, raising faithfulness 3.7x to 0.826.

  4. MoCA-Agent: A Market-of-Claims Code Agent for Financial and Numerical Reasoning

    cs.AI 2026-06 unverdicted novelty 5.0 of 10

    MoCA-Agent decomposes questions into typed atomic claims, clears them via trader-agent markets into confidence-weighted decisions, synthesizes and verifies executable Python code, and reports strong benchmark scores i...

  5. TabClaw: An Interactive and Self-Evolving Agent for Spreadsheet Manipulation and Table Reasoning

    cs.CL 2026-06 unverdicted novelty 5.0 of 10

    TabClaw is an interactive LLM agent for spreadsheets that exposes editable plans, uses parallel specialist agents, streams ReAct loops, and distills skills from user feedback, reporting improved benchmark task completion.

  6. TableMind: An Autonomous Programmatic Agent for Tool-Augmented Table Reasoning

    cs.AI 2025-09 conditional novelty 5.0 of 10

    TableMind, a two-stage SFT-plus-RL agent trained on an 8B model, reports state-of-the-art results on three table reasoning benchmarks.

  7. When TableQA Meets Noise: A Dual Denoising Framework for Complex Questions and Large-scale Tables

    cs.CL 2025-09 unverdicted novelty 4.0 of 10

    EnoTab is a dual denoising framework for TableQA that performs evidence-based question denoising via semantic unit decomposition and evidence tree-guided table pruning with post-order rollback to improve performance o...

  8. MRT at IberLEF-2025 PRESTA Task: Maximizing Recovery from Tables with Multiple Steps

    cs.CL 2025-07 conditional novelty 4.0 of 10

    MRT, an LLM code-generation pipeline for Spanish table QA, achieves 85% accuracy on the IberLEF 2025 PRESTA test set.

  9. Table Question Answering in the Era of Large Language Models: A Comprehensive Survey of Tasks, Methods, and Evaluation

    cs.CL 2025-10 unverdicted novelty 3.0 of 10

    A survey that categorizes TQA benchmarks and LLM modeling strategies by challenges while identifying underexplored areas such as reinforcement learning.

Pith tools