Concordia aligns synthetic table generation with federated validation utility via client-side utility scorers and group-relative policy optimization to improve LLM adaptation on non-IID tabular tasks.
arXiv preprint arXiv:2502.06555 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Tab-PE extends Private Evolution to tabular data with heuristic operators, outperforming AIM by up to 10% classification accuracy and 28x speed on high-order correlation datasets under differential privacy.
citing papers explorer
-
Concordia: Self-Improving Synthetic Tables for Federated LLMs
Concordia aligns synthetic table generation with federated validation utility via client-side utility scorers and group-relative policy optimization to improve LLM adaptation on non-IID tabular tasks.
-
Differentially Private Synthetic Data via APIs 4: Tabular Data
Tab-PE extends Private Evolution to tabular data with heuristic operators, outperforming AIM by up to 10% classification accuracy and 28x speed on high-order correlation datasets under differential privacy.