NAP^2: A Benchmark for Naturalness and Privacy-Preserving Text Rewriting by Learning from Human
This addresses privacy concerns for users of cloud-based LLMs, though it is incremental as it builds on prior anonymization work with a new benchmark.
The paper tackles privacy risks in cloud-based LLMs by proposing human-inspired text rewriting strategies (deletion and abstraction) to sanitize sensitive data, resulting in more natural rewrites and a better balance between privacy and utility as shown in experiments.
The widespread use of cloud-based Large Language Models (LLMs) has heightened concerns over user privacy, as sensitive information may be inadvertently exposed during interactions with these services. To protect privacy before sending sensitive data to those models, we suggest sanitizing sensitive text using two common strategies used by humans: i) deleting sensitive expressions, and ii) obscuring sensitive details by abstracting them. To explore the issues and develop a tool for text rewriting, we curate the first corpus, coined NAP^2, through both crowdsourcing and the use of large language models (LLMs). Compared to the prior works on anonymization, the human-inspired approaches result in more natural rewrites and offer an improved balance between privacy protection and data utility, as demonstrated by our extensive experiments. Researchers interested in accessing the dataset are encouraged to contact the first or corresponding author via email.