Research

Paper

AI LLM March 03, 2026

PrivMedChat: End-to-End Differentially Private RLHF for Medical Dialogue Systems

Authors

Sudip Bhujel

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 risks, enabling empirical membership inference and extraction of rare training-set content. We present PrivMedChat, an end-to-end framework for differentially private RLHF (DP-RLHF) for medical dialogue. Our design enforces differential privacy at every training stage that directly accesses dialogue-derived supervision: (i) Differential Private Stochastic Gradient Descent (DP-SGD) for medical SFT and (ii) DP-SGD for reward model learning from preference pairs. To limit additional privacy expenditure during alignment, we apply DP-SGD to the PPO actor and critic when operating on dialogue-derived prompts, while the reward model remains fixed after DP training. We also introduce an annotation-free preference construction strategy that pairs physician responses with filtered non-expert generations to produce scalable preference data without clinician labeling. Experiments on medical dialogue benchmarks show that PrivMedChat at $\varepsilon=7$ achieves the highest ROUGE-L of 0.156 among all DP models, reduces clinical hallucinations to 1.4% and harmful advice to 0.4%, and obtains the highest overall score of 2.86 in a 3-model LLM-jury evaluation, while producing membership-inference signals that are near chance (AUC 0.510-0.555). We open-source our code at https://github.com/sudip-bhujel/privmedchat.

Metadata

arXiv ID: 2603.03054
Provider: ARXIV
Primary Category: cs.CL
Published: 2026-03-03
Fetched: 2026-03-04 03:41

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.03054v1</id>\n    <title>PrivMedChat: End-to-End Differentially Private RLHF for Medical Dialogue Systems</title>\n    <updated>2026-03-03T14:53:20Z</updated>\n    <link href='https://arxiv.org/abs/2603.03054v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.03054v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>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 risks, enabling empirical membership inference and extraction of rare training-set content. We present PrivMedChat, an end-to-end framework for differentially private RLHF (DP-RLHF) for medical dialogue. Our design enforces differential privacy at every training stage that directly accesses dialogue-derived supervision: (i) Differential Private Stochastic Gradient Descent (DP-SGD) for medical SFT and (ii) DP-SGD for reward model learning from preference pairs. To limit additional privacy expenditure during alignment, we apply DP-SGD to the PPO actor and critic when operating on dialogue-derived prompts, while the reward model remains fixed after DP training.\n  We also introduce an annotation-free preference construction strategy that pairs physician responses with filtered non-expert generations to produce scalable preference data without clinician labeling. Experiments on medical dialogue benchmarks show that PrivMedChat at $\\varepsilon=7$ achieves the highest ROUGE-L of 0.156 among all DP models, reduces clinical hallucinations to 1.4% and harmful advice to 0.4%, and obtains the highest overall score of 2.86 in a 3-model LLM-jury evaluation, while producing membership-inference signals that are near chance (AUC 0.510-0.555). We open-source our code at https://github.com/sudip-bhujel/privmedchat.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CL'/>\n    <published>2026-03-03T14:53:20Z</published>\n    <arxiv:primary_category term='cs.CL'/>\n    <author>\n      <name>Sudip Bhujel</name>\n    </author>\n  </entry>"
}