pith. sign in

Privacy-preserving retrieval-augmented generation with differential privacy

3 Pith papers cite this work. Polarity classification is still indexing.

3 Pith papers citing it

citation-role summary

background 2

citation-polarity summary

fields

cs.CR 2 cs.AI 1

years

2026 2 2025 1

roles

background 1

polarities

background 1

clear filters

representative citing papers

SynBench: A Benchmark for Differentially Private Text Generation

cs.AI · 2025-09-18 · conditional · novelty 7.0

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

Showing 1 of 1 citing paper after filters.

  • SynBench: A Benchmark for Differentially Private Text Generation cs.AI · 2025-09-18 · conditional · none · ref 27

    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.