AI RESEARCH
SAGE: Sparse Adaptive Guidance for Dependency-Aware Tabular Data Generation
arXiv CS.LG
•
ArXi:2604.24368v1 Announce Type: new Generating high-fidelity synthetic tabular data remains a critical challenge for enhancing data availability in privacy-sensitive and low-resource domains. Recent approaches leverage LLMs by representing table rows as sequences, yet suffer from two fundamental limitations: (1) they model feature dependencies densely,