TabulaX: Leveraging Large Language Models for Multi-Class Table Transformations

Summary: TabulaX classifies columns into string, numerical, algorithmic, or general transformations, then uses LLMs to synthesize tailored, human-interpretable formulas/code. It broadens transformation coverage and improves accuracy over prior automation methods on real-world data. (summarized by gpt-5.6-luna on Jul 24 2026)

Paper ID: h6c344460b4e7be01
Venue: VLDB
Year: 2025
Pagerank: 5.4228804e-05
Overall Rank: 7,933 | 46.69%
DOI: 10.14778/3749646.3749657
PDF: Download (CC BY-NC-ND 4.0)

Incoming Non-self Citations Over Time

Authors

1. Arash Dargahi Nobari (University of Alberta)
2. Davood Rafiei (University of Alberta)

BibTeX Citation

@article{nobari_vldb25,
        title = {{TabulaX: Leveraging Large Language Models for Multi-Class Table Transformations}},
        author = {Nobari, Arash Dargahi and Rafiei, Davood},
        journal = {PVLDB},
        series = {{VLDB} '25},
        volume = {18},
        number = {11},
        pages = {3826--3839},
        doi = {10.14778/3749646.3749657},
        url = {https://doi.org/10.14778/3749646.3749657},
        year = {2025}
}

Incoming Citations (Sorted by Pagerank)

Showing 4 of 4 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
7,531	Auto-Prep: Holistic Prediction of Data Preparation Steps for Self-Service Business Intelligence	2025	VLDB	5.4994676e-05
10,724	SQL-Exchange: Transforming SQL Queries Across Domains	2026	VLDB	4.9769913e-05
10,801	BookRAG: A Hierarchical Structure-aware Index-based Approach for Retrieval-Augmented Generation on Complex Documents	2026	VLDB	4.9769913e-05
10,847	EcoTable: Cost-effective Table Integration in Data Lakes for Natural Language Queries	2026	VLDB	4.9769913e-05

Outgoing Citations (Sorted by Pagerank)

Showing 18 of 18 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank	Cited Paper	Year	Venue	Pagerank
134	Deep Entity Matching with Pre-Trained Language Models	2021	VLDB	0.00030042569
377	TURL: Table Understanding through Representation Learning	2021	VLDB	0.00019564011
1,095	BlinkFill: Semi-supervised Programming By Example for Syntactic String Transformations	2016	VLDB	0.00012048043
1,115	Foofah: Transforming Data By Example	2017	SIGMOD	0.00011958625
1,840	From Natural Language Processing to Neural Databases	2021	VLDB	9.5271706e-05
1,977	Table-GPT: Table Fine-tuned GPT for Diverse Table Tasks	2024	SIGMOD	9.2760522e-05
1,993	RPT: Relational Pre-trained Transformer Is Almost All You Need towards Democratizing Data Preparation	2021	VLDB	9.2348951e-05
2,160	Open Data Integration	2018	VLDB	8.9373643e-05
2,613	Auto-Join: Joining Tables by Leveraging Transformations	2017	VLDB	8.2229082e-05
2,744	Transform-Data-by-Example (TDE): An Extensible Search Engine for Data Transformations	2018	VLDB	8.064168e-05
3,750	Discovering Linkage Points over Web Data	2013	VLDB	7.0497806e-05
4,159	Integrating Data Lake Tables	2023	VLDB	6.7687144e-05
4,204	SEMA-JOIN: Joining Semantically-Related Tables Using Big Table Corpora	2015	VLDB	6.7331936e-05
4,972	Auto-FuzzyJoin: Auto-Program Fuzzy Similarity Joins Without Labeled Examples	2021	SIGMOD	6.3300201e-05
5,100	Explaining Dataset Changes for Semantic Data Versioning with Explain-Da-V	2023	VLDB	6.271266e-05
5,686	DTT: An Example-Driven Tabular Transformer for Joinability by Leveraging Large Language Models	2024	SIGMOD	6.0347166e-05
7,150	Transform-Data-by-Example (TDE): Extensible Data Transformation in Excel	2018	SIGMOD	5.5963926e-05
8,143	Synthesizing Mapping Relationships Using Table Corpus	2017	SIGMOD	5.3898955e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	8,271	Automated Data Visualization from Natural Language via Large Language Models: An Exploratory Study	2024	SIGMOD
2	11,278	Weak-to-Strong Prompts with Lightweight-to-Powerful LLMs for High-Accuracy, Low-Cost, and Explainable Data Transformation	2025	VLDB
3	11,419	TableCopilot: A Table Assistant Empowered by Natural Language Conditional Table Discovery	2025	VLDB
4	4,426	Auto-Transform: Learning-to-Transform by Patterns	2020	VLDB
5	13,590	SciTables: A Dataset and Evaluation Framework for Complex Table-to-Text Generation	2026	VLDB
6	6,139	DataXFormer: Leveraging the Web for Semantic Transformations	2015	CIDR
7	1,977	Table-GPT: Table Fine-tuned GPT for Diverse Table Tasks	2024	SIGMOD
8	3,423	AutoTQA: Towards Autonomous Tabular Question Answering through Multi-Agent Large Language Models	2024	VLDB
9	4,631	Transformers for Tabular Data Representation: A Tutorial on Models and Applications	2022	VLDB
10	5,686	DTT: An Example-Driven Tabular Transformer for Joinability by Leveraging Large Language Models	2024	SIGMOD