Local Language Models for Context-Aware Adaptive Anonymization of Sensitive Text

2026-01-21

AI Summary

Traditional approaches to sensitive text anonymization rely on fixed rules or manual processing, suffering from low efficiency, poor consistency, and insufficient contextual awareness, which often leads to privacy leaks or data distortion. This work proposes a Structured Framework for Adaptive Anonymization (SFAA), the first method to leverage local large language models—such as LLaMA and Phi—for context-aware anonymization of qualitative research texts. SFAA employs a three-stage pipeline of detection, classification, and adaptive anonymization, dynamically integrating four strategies: rule-based substitution, context-aware rewriting, generalization, and suppression, while aligning with privacy regulations including GDPR and HIPAA. Experimental results demonstrate that the Phi model identifies over 91% of sensitive information across 175 interview transcripts, with 94.8% of anonymized outputs preserving the original sentiment orientation, outperforming manual review in both accuracy and fidelity.

Technology Category

• Natural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy
• Machine Learning: Privacy
• Philosophy and Ethics of AI: Privacy & Security

Application Category

• Search and Retrieval-Augmented AI: Large language models for search
• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization
• Security and Privacy: Data transparency and provenance

Abstract

Qualitative research often contains personal, contextual, and organizational details that pose privacy risks if not handled appropriately. Manual anonymization is time-consuming, inconsistent, and frequently omits critical identifiers. Existing automated tools tend to rely on pattern matching or fixed rules, which fail to capture context and may alter the meaning of the data. This study uses local LLMs to build a reliable, repeatable, and context-aware anonymization process for detecting and anonymizing sensitive data in qualitative transcripts. We introduce a Structured Framework for Adaptive Anonymizer (SFAA) that includes three steps: detection, classification, and adaptive anonymization. The SFAA incorporates four anonymization strategies: rule-based substitution, context-aware rewriting, generalization, and suppression. These strategies are applied based on the identifier type and the risk level. The identifiers handled by the SFAA are guided by major international privacy and research ethics standards, including the GDPR, HIPAA, and OECD guidelines. This study followed a dual-method evaluation that combined manual and LLM-assisted processing. Two case studies were used to support the evaluation. The first includes 82 face-to-face interviews on gamification in organizations. The second involves 93 machine-led interviews using an AI-powered interviewer to test LLM awareness and workplace privacy. Two local models, LLaMA and Phi were used to evaluate the performance of the proposed framework. The results indicate that the LLMs found more sensitive data than a human reviewer. Phi outperformed LLaMA in finding sensitive data, but made slightly more errors. Phi was able to find over 91% of the sensitive data and 94.8% kept the same sentiment as the original text, which means it was very accurate, hence, it does not affect the analysis of the qualitative data.

Problem

• anonymization
• sensitive text
• context-aware
• privacy
• qualitative research

Innovation

• Local LLMs
• Context-Aware Anonymization
• Structured Framework for Adaptive Anonymizer
• Privacy-Preserving NLP
• Qualitative Data Anonymization