POPri uses client similarity scores as RL rewards to DPO-tune an LLM for DP synthetic data generation, outperforming prior private evolution baselines on next-token prediction and classification.
Towards private synthetic text generation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
POPri: Private Federated Learning using Preference-Optimized Synthetic Data
POPri uses client similarity scores as RL rewards to DPO-tune an LLM for DP synthetic data generation, outperforming prior private evolution baselines on next-token prediction and classification.