# Robust Privacy Amidst Innovation with Large Language Models Through a Critical Assessment of the Risks

arXiv: https://arxiv.org/abs/2407.16166 · HTML: https://mlsanity.com/paper/2407.16166/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 33 references that are in the map.
- First posted on arXiv 23 Jul 2024.

## Builds on (most cited first, 10 of 10)

- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [BioBERT: a pre-trained biomedical language representation model for biomedical text mining](https://mlsanity.com/paper/1901.08746/) (2019)
- [A Study of Generative Large Language Model for Medical Research and Healthcare](https://mlsanity.com/paper/2305.13523/) (2023)
- [A Label Attention Model for ICD Coding from Clinical Text](https://mlsanity.com/paper/2007.06351/) (2020)
- [A Review of Keyphrase Extraction](https://mlsanity.com/paper/1905.05044/) (2019)
- [Are Small Language Models Ready to Compete with Large Language Models for Practical Applications?](https://mlsanity.com/paper/2406.11402/) (2024)
- [Natural Language Processing with Deep Learning for Medical Adverse Event Detection from Free-Text Medical Narratives: A Case Study of Detecting Total Hip Replacement Dislocation](https://mlsanity.com/paper/2004.08333/) (2020)
- [Verbing Weirds Language (Models): Evaluation of English Zero-Derivation in Five LLMs](https://mlsanity.com/paper/2403.17856/) (2024)
- [Extracting periodontitis diagnosis in clinical notes with RoBERTa and regular expression](https://mlsanity.com/paper/2311.10809/) (2023)
- [Attention on Personalized Clinical Decision Support System: Federated Learning Approach](https://mlsanity.com/paper/2401.11736/) (2024)

## Built on by (most cited first, 3 of 3)

- [Thousand Voices of Trauma: A Large-Scale Synthetic Dataset for Modeling Prolonged Exposure Therapy Conversations](https://mlsanity.com/paper/2504.13955/) (2025)
- [A Scoping Review of Synthetic Data Generation by Language Models in Biomedical Research and Application: Data Utility and Quality Perspectives](https://mlsanity.com/paper/2506.16594/) (2025)
- [Self-Prompting Small Language Models for Privacy-Sensitive Clinical Information Extraction](https://mlsanity.com/paper/2605.04221/) (2026)

## Abstract (arXiv)

This study examines integrating EHRs and NLP with large language models (LLMs) to improve healthcare data management and patient care. It focuses on using advanced models to create secure, HIPAA-compliant synthetic patient notes for biomedical research. The study used de-identified and re-identified MIMIC III datasets with GPT-3.5, GPT-4, and Mistral 7B to generate synthetic notes. Text generation employed templates and keyword extraction for contextually relevant notes, with one-shot generation for comparison. Privacy assessment checked PHI occurrence, while text utility was tested using an ICD-9 coding task. Text quality was evaluated with ROUGE and cosine similarity metrics to measure semantic similarity with source notes. Analysis of PHI occurrence and text utility via the ICD-9 coding task showed that the keyword-based method had low risk and good performance. One-shot generation showed the highest PHI exposure and PHI co-occurrence, especially in geographic location and date categories. The Normalized One-shot method achieved the highest classification accuracy. Privacy analysis revealed a critical balance between data utility and privacy protection, influencing future data use and sharing. Re-identified data consistently outperformed de-identified data. This study demonstrates the effectiveness of keyword-based methods in generating privacy-protecting synthetic clinical notes that retain data usability, potentially transforming clinical data-sharing practices. The superior performance of re-identified over de-identified data suggests a shift towards methods that enhance utility and privacy by using dummy PHIs to perplex privacy attacks.