Preprint · 2026 · Open access
PrivMedChat: End-to-End Differentially Private RLHF for Medical Dialogue Systems
arXiv (Cornell University) · Published 3 March 2026 · DOI 10.48550/arxiv.2603.03054
In brief
“PrivMedChat: End-to-End Differentially Private RLHF for Medical Dialogue Systems” is a 2026 preprint by Sudip Bhujel, published in arXiv (Cornell University). OpenAlex counts 0 citations as of 19 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).
- Citations
- 0
- References
- 40
- Authors
- 1
Abstract
Large language models are increasingly used for patient-facing medical assistance and clinical decision support, but adapting them to clinical dialogue often requires supervision derived from doctor-patient conversations that may contain sensitive information. Conventional supervised fine-tuning and reinforcement learning from human feedback (RLHF) can amplify memorization, enabling membership inference and disclosure of rare training-set details. We present PrivMedChat (Private Medical Chat), an end-to-end framework for differentially private RLHF (DP-RLHF) for medical dialogue systems. Our approach enforces differential privacy at each training stage that accesses dialogue-derived supervision, combining DP-SGD for supervised fine-tuning and reward model learning from preference pairs, and DP-aware policy optimization for alignment. To avoid costly clinician labeling, we introduce an annotation-free preference construction strategy that pairs physician responses with filtered non-expert generations. We evaluate PrivMedChat across medical dialogue tasks and assess utility, safety, and privacy under consistent privacy accounting, thereby providing a practical pathway to align medical chatbots while offering formal privacy guarantees. We open-source our code at https://github.com/sudip-bhujel/privmedchat.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Bhujel, S. (2026). PrivMedChat: End-to-End Differentially Private RLHF for Medical Dialogue Systems. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2603.03054
MLA 9
Bhujel, Sudip. “PrivMedChat: End-to-End Differentially Private RLHF for Medical Dialogue Systems.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2603.03054.
Chicago
Bhujel, Sudip. 2026. “PrivMedChat: End-to-End Differentially Private RLHF for Medical Dialogue Systems.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2603.03054.
Harvard
Bhujel, S. (2026) ‘PrivMedChat: End-to-End Differentially Private RLHF for Medical Dialogue Systems’, arXiv (Cornell University). doi:10.48550/arxiv.2603.03054.
IEEE
S. Bhujel, “PrivMedChat: End-to-End Differentially Private RLHF for Medical Dialogue Systems,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2603.03054.
BibTeX
@misc{bhujel2026privmedchat,
title = {{PrivMedChat: End-to-End Differentially Private RLHF for Medical Dialogue Systems}},
author = {Bhujel, Sudip},
howpublished = {arXiv (Cornell University)},
year = {2026},
doi = {10.48550/arxiv.2603.03054},
url = {https://doi.org/10.48550/arxiv.2603.03054}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- differential privacy
- reinforcement learning from human feedback
- medical dialogue systems
- healthcare chatbots
- privacy-preserving fine-tuning
- DP-SGD
- reward modeling
- membership inference
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Bhujel, S. (2026). PrivMedChat: End-to-End Differentially Private RLHF for Medical Dialogue Systems. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2603.03054
How many times has this paper been cited?
0 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.
Who wrote this paper?
Sudip Bhujel.
What is the DOI of this paper?
10.48550/arxiv.2603.03054, permanently at https://doi.org/10.48550/arxiv.2603.03054. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.