Answers are grounded in this paper and cite their sources.
Organizations increasingly rely on relational data containing sensitive personal information for downstream tasks. A common approach is to release synthetic data as a privacy-preserving substitute, typically by learning a generative model and sampling from it. Differential privacy (DP) provides a formal guarantee of data privacy, and existing data synthesis systems aim to balance its inherent trade-off between data privacy and task utility. The advent of pretrained large language models (LLMs) has reshaped this trade-off landscape: on the utility side, LLMs possess stronger representational capabilities and encode extensive prior knowledge that does not consume the privacy budget, leading to improved task utility; on the other hand, enforcing differential privacy for LLM-based relational data synthesis introduces new technical challenges. We present P rism, an end-to-end framework for DP relational data synthesis using LLMs. P rism privatizes knowledge transfer from an ensemble of teacher LLMs to a student generator via DP output aggregation. We introduce three key innovations in the aggregation mechanism to address LLM-specific challenges, including 1) token pruning with tries to minimize teacher queries and hence the privacy cost; 2) a data-dependent DP mechanism that adaptively scales noise for efficient budget use; and 3) probabilistic sampling with threshold filtering to reduce bias and preserve diversity. Extensive empirical results across twelve experiments show that Prism achieves substantially higher predictive utility than eight state-of-the-art methods under the same privacy budget.
No takes yet. Share an insight, caveat, or question.
Guan et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: