ChatGPT for Us: Preserving Data Privacy in ChatGPT via Dialogue Text Ambiguation to Expand Mental Health Care Delivery

TL;DR

This paper introduces a text ambiguation framework to preserve user privacy in ChatGPT while addressing mental health concerns, demonstrating that privacy-preserved responses remain helpful and relevant.

Contribution

It proposes a novel text ambiguation method to enhance privacy in ChatGPT for sensitive domains like mental health care.

Findings

ChatGPT can generate helpful responses with ambiguous input.

Privacy-preserved responses maintain relevance and helpfulness.

The framework enables privacy in sensitive dialogue applications.

Abstract

Large language models have been useful in expanding mental health care delivery. ChatGPT, in particular, has gained popularity for its ability to generate human-like dialogue. However, data-sensitive domains -- including but not limited to healthcare -- face challenges in using ChatGPT due to privacy and data-ownership concerns. To enable its utilization, we propose a text ambiguation framework that preserves user privacy. We ground this in the task of addressing stress prompted by user-provided texts to demonstrate the viability and helpfulness of privacy-preserved generations. Our results suggest that chatGPT recommendations are still able to be moderately helpful and relevant, even when the original user text is not provided.