# Leveraging Semantic Triples for Private Document Generation with Local Differential Privacy Guarantees

## TL;DR

This paper introduces DP-ST, a method leveraging semantic triples for private document generation under local differential privacy, balancing privacy and utility with improved coherence at lower privacy parameters.

## Contribution

The paper proposes DP-ST, a novel approach using semantic triples and neighborhood-aware privacy to enhance private text generation under local differential privacy constraints.

## Key findings

- Effective private document generation at lower ε values.
- Neighborhood-aware approach improves coherence and utility.
- Combining with LLM post-processing enhances text quality.

## Abstract

Many works at the intersection of Differential Privacy (DP) in Natural Language Processing aim to protect privacy by transforming texts under DP guarantees. This can be performed in a variety of ways, from word perturbations to full document rewriting, and most often under local DP. Here, an input text must be made indistinguishable from any other potential text, within some bound governed by the privacy parameter $\varepsilon$. Such a guarantee is quite demanding, and recent works show that privatizing texts under local DP can only be done reasonably under very high $\varepsilon$ values. Addressing this challenge, we introduce DP-ST, which leverages semantic triples for neighborhood-aware private document generation under local DP guarantees. Through the evaluation of our method, we demonstrate the effectiveness of the divide-and-conquer paradigm, particularly when limiting the DP notion (and privacy guarantees) to that of a privatization neighborhood. When combined with LLM post-processing, our method allows for coherent text generation even at lower $\varepsilon$ values, while still balancing privacy and utility. These findings highlight the importance of coherence in achieving balanced privatization outputs at reasonable $\varepsilon$ levels.