# In-Context Learning for Preserving Patient Privacy: A Framework for Synthesizing Realistic Patient Portal Messages

arXiv: https://arxiv.org/abs/2411.06549 · HTML: https://mlsanity.com/paper/2411.06549/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 19 references that are in the map.
- First posted on arXiv 10 Nov 2024.

## Builds on (most cited first, 6 of 6)

- [Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs](https://mlsanity.com/paper/2311.04892/) (2023)
- [Evaluating Large Language Model Biases in Persona-Steered Generation](https://mlsanity.com/paper/2405.20253/) (2024)
- [Generating Faithful Synthetic Data with Large Language Models: A Case Study in Computational Social Science](https://mlsanity.com/paper/2305.15041/) (2023)
- [Large Language Model Instruction Following: A Survey of Progresses and Challenges](https://mlsanity.com/paper/2303.10475/) (2023)
- [Students Need More Attention: BERT-based AttentionModel for Small Data with Application to AutomaticPatient Message Triage](https://mlsanity.com/paper/2006.11991/) (2020)
- [Statistical Depth for Ranking and Characterizing Transformer-Based Text Embeddings](https://mlsanity.com/paper/2310.15010/) (2023)

## Built on by (most cited first, 2 of 2)

- [StaAgent: An Agentic Framework for Testing Static Analyzers](https://mlsanity.com/paper/2507.15892/) (2025)
- [How Much Would a Clinician Edit This Draft? Evaluating LLM Alignment for Patient Message Response Drafting](https://mlsanity.com/paper/2601.11344/) (2026)

## Abstract (arXiv)

Since the COVID-19 pandemic, clinicians have seen a large and sustained influx in patient portal messages, significantly contributing to clinician burnout. To the best of our knowledge, there are no large-scale public patient portal messages corpora researchers can use to build tools to optimize clinician portal workflows. Informed by our ongoing work with a regional hospital, this study introduces an LLM-powered framework for configurable and realistic patient portal message generation. Our approach leverages few-shot grounded text generation, requiring only a small number of de-identified patient portal messages to help LLMs better match the true style and tone of real data. Clinical experts in our team deem this framework as HIPAA-friendly, unlike existing privacy-preserving approaches to synthetic text generation which cannot guarantee all sensitive attributes will be protected. Through extensive quantitative and human evaluation, we show that our framework produces data of higher quality than comparable generation methods as well as all related datasets. We believe this work provides a path forward for (i) the release of large-scale synthetic patient message datasets that are stylistically similar to ground-truth samples and (ii) HIPAA-friendly data generation which requires minimal human de-identification efforts.