RL-Finetuned LLMs for Privacy-Preserving Synthetic Rewriting

TL;DR

This paper introduces a reinforcement learning method to fine-tune large language models for generating privacy-preserving synthetic text that balances data utility and privacy protection.

Contribution

It proposes a novel RL framework that jointly optimizes for privacy, semantic fidelity, and diversity using a composite reward function incorporating structural privacy cues.

Findings

Enhanced author obfuscation and privacy metrics

Maintained semantic quality of generated text

Scalable, model-agnostic privacy-preserving data generation

Abstract

The performance of modern machine learning systems depends on access to large, high-quality datasets, often sourced from user-generated content or proprietary, domain-specific corpora. However, these rich datasets inherently contain sensitive personal information, raising significant concerns about privacy, data security, and compliance with regulatory frameworks. While conventional anonymization techniques can remove explicit identifiers, such removal may result in performance drop in downstream machine learning tasks. More importantly, simple anonymization may not be effective against inference attacks that exploit implicit signals such as writing style, topical focus, or demographic cues, highlighting the need for more robust privacy safeguards during model training. To address the challenging issue of balancing user privacy and data utility, we propose a reinforcement learning framework that fine-tunes a large language model (LLM) using a composite reward function that jointly optimizes for explicit and implicit privacy, semantic fidelity, and output diversity. To effectively capture population level regularities, the privacy reward combines semantic cues with structural patterns derived from a minimum spanning tree (MST) over latent representations. By modeling these privacy-sensitive signals in their distributional context, the proposed approach guides the model to generate synthetic rewrites that preserve utility while mitigating privacy risks. Empirical results show that the proposed method significantly enhances author obfuscation and privacy metrics without degrading semantic quality, providing a scalable and model-agnostic solution for privacy preserving data generation in the era of large language models.