ContinuousBench shows non-private synthetic text transfers corpus-specific capabilities while state-of-the-art DP methods fail to do so even at ε=100.
Differentially Private Language Models for Secure Data Sharing
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
SynBench benchmarks DP text generators across nine datasets and uses a new MIA to show that public pre-training on portions of private data overestimates synthetic text quality and breaks DP privacy bounds.
citing papers explorer
-
ContinuousBench: Can Differentially Private Synthetic Text Improve Capabilities?
ContinuousBench shows non-private synthetic text transfers corpus-specific capabilities while state-of-the-art DP methods fail to do so even at ε=100.
-
SynBench: A Benchmark for Differentially Private Text Generation
SynBench benchmarks DP text generators across nine datasets and uses a new MIA to show that public pre-training on portions of private data overestimates synthetic text quality and breaks DP privacy bounds.