Text Sanitization Beyond Specific Domains: Zero-Shot Redaction & Substitution with Large Language Models
This addresses the need for generalizable and less disruptive text sanitization methods in information systems, though it is incremental as it builds on existing LLM capabilities.
The paper tackles the problem of text sanitization for privacy preservation by introducing a zero-shot technique using Large Language Models to detect and substitute sensitive information, achieving strong performance in protecting privacy while maintaining text coherence and contextual information.
In the context of information systems, text sanitization techniques are used to identify and remove sensitive data to comply with security and regulatory requirements. Even though many methods for privacy preservation have been proposed, most of them are focused on the detection of entities from specific domains (e.g., credit card numbers, social security numbers), lacking generality and requiring customization for each desirable domain. Moreover, removing words is, in general, a drastic measure, as it can degrade text coherence and contextual information. Less severe measures include substituting a word for a safe alternative, yet it can be challenging to automatically find meaningful substitutions. We present a zero-shot text sanitization technique that detects and substitutes potentially sensitive information using Large Language Models. Our evaluation shows that our method excels at protecting privacy while maintaining text coherence and contextual information, preserving data utility for downstream tasks.