Datasets › TabFact

TabFact

Introduced by Wenhu Chen et al. in TabFact: A Large-scale Dataset for Table-based Fact Verification5 Sep 2019 archive 2025-07-28

TabFact is a large-scale dataset which consists of 117,854 manually annotated statements with regard to 16,573 Wikipedia tables, their relations are classified as ENTAILED and REFUTED. TabFact is the first dataset to evaluate language inference on structured data, which involves mixed reasoning skills in both symbolic and linguistic aspects.

Source: GitHub

Homepage Benchmarks Papers JSON

Benchmarks archive 2025-07-28

All 2 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

		First row (archive order)	Paper	Code
Table-based Fact Verification	TabFact	ARTEMIS-DA Test 93.1	ARTEMIS-DA: An Advanced Reasoning and Transformation...	—	15	Compare
Natural Language Inference	TabFact	ChatGPT 3.5 SpatialFormat Accuracy 70.1	LAPDoc: Layout-Aware Prompting for Documents	—	1	Compare

Papers archive 2025-07-28

15 shown of 15 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 129. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

			Date	Samples run Syntology
ARTEMIS-DA: An Advanced Reasoning and Transformation Engine for Multi-Step Insight Synthesis in Data Analytics	0	1	18 Dec 2024	not harvested
NormTab: Improving Symbolic Reasoning in LLMs Through Tabular Data Normalization	1	1	25 Jun 2024	not harvested
Efficient Prompting for LLM-based Generative Internet of Things	0	1	14 Jun 2024	not harvested
TabSQLify: Enhancing Reasoning Capabilities of LLMs Through Table Decomposition	2	1	15 Apr 2024	ran 7 of 15 samples (8 unverified; 15 pointer-only for licence)
LAPDoc: Layout-Aware Prompting for Documents	0	1	15 Feb 2024	not harvested
Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding	2	1	9 Jan 2024	ran 6 of 8 samples (2 unverified)
Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning	2	1	31 Jan 2023	not harvested
PASTA: Table-Operations Aware Fact Verification via Sentence-Table Cloze Pre-training	1	1	5 Nov 2022	ran 1 of 6 samples (5 unverified)
ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examples	1	1	22 Oct 2022	ran 0 of 11 samples (11 unverified)
Binding Language Models in Symbolic Languages	4	1	6 Oct 2022	ran 2 of 3 samples (1 unverified)
UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models	1	1	16 Jan 2022	ran 1 of 5 samples (4 unverified)
Table-based Fact Verification with Salience-aware Learning	1	1	9 Sep 2021	not harvested
TAPEX: Table Pre-training via Learning a Neural SQL Executor	4	1	16 Jul 2021	not harvested
Understanding tables with intermediate pre-training	1	1	1 Oct 2020	not harvested
TabFact: A Large-scale Dataset for Table-based Fact Verification	1	2	5 Sep 2019	ran 2 of 3 samples (1 unverified; 2 pointer-only for licence)

Dataset loaders archive 2025-07-28

huggingface.co/datasets/wenhu/tab_fact huggingface/datasetstfpytorchjax

huggingface.co/datasets/tab_fact huggingface/datasetstfpytorchjax

2 loaders as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

Natural Language Inference Table-based Fact Verification

License archive 2025-07-28

CC BY 4.0

Modalities archive 2025-07-28

Texts

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

TabFact

1 variant name, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections