CATS : An enhanced framework in LLM-based tabular data synthesis by correlation augmentation
Authors:
- Luyu ChenLCLuyu Chen
- Mingxuan JiangMJMingxuan Jiang
- Ziyue DaiZDZiyue Dai
- Sen LiuSLSen Liu
- Hongfeng ChaiHCHongfeng Chai
- 30 April 2026
- journal article
- Published by Elsevier in Expert Systems with Applications
- Vol. 325
Abstract
No abstract availableFunding Information
- Chinese Academy of Engineering (2024-JZ-0301)
- National Key Research and Development Program of China
- Key Technologies Research and Development Program (2023YFC3305200)
- Natural Science Foundation of Shanghai Municipality (23ZR1404900)
This publication has 15 references indexed in Scilit:
- LLMOverTab: Tabular data augmentation with language model-driven oversamplingExpert Systems with Applications, 2024
- TabSAL: Synthesizing Tabular data with Small agent Assisted Language modelsKnowledge-Based Systems, 2024
- Data generation scheme for photovoltaic power forecasting using Wasserstein GAN with gradient penalty combined with autoencoder and regression modelsExpert Systems with Applications, 2024
- End-to-end approach of multi-grained embedding of categorical features in tabular dataInformation Processing & Management, 2024
- ChatGPT outperforms crowd workers for text-annotation tasksProceedings of the National Academy of Sciences, 2023
- Parameter-efficient fine-tuning of large-scale pre-trained language modelsNature Machine Intelligence, 2023
- AI in Finance: Challenges, Techniques, and OpportunitiesACM Computing Surveys, 2022
- Data scarcity, robustness and extreme multi-label classificationMachine Learning, 2019
- Using Spearman's correlation coefficients for exploratory data analysis on big datasetConcurrency and Computation: Practice and Experience, 2015
- The Chi-square test of independenceBiochemia Medica, 2013