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

• URL: http://arxiv.org/abs/2603.03054v2
• Date: Sat, 07 Mar 2026 16:16:50 GMT
• Title: PrivMedChat: End-to-End Differentially Private RLHF for Medical Dialogue Systems
• Abstract summary: We present PrivMedChat, an end-to-end framework for differentially private RLHF for medical dialogue systems.<n>Our approach enforces differential privacy at each training stage that accesses dialogue-derived supervision.<n>We evaluate PrivMedChat across medical dialogue tasks and assess utility, safety, and privacy under consistent privacy accounting.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• A Federated and Parameter-Efficient Framework for Large Language Model Training in Medicine [59.78991974851707]
  Large language models (LLMs) have demonstrated strong performance on medical benchmarks, including question answering and diagnosis.<n>Most medical LLMs are trained on data from a single institution, which faces limitations in generalizability and safety in heterogeneous systems.<n>We introduce the model-agnostic and parameter-efficient federated learning framework for adapting LLMs to medical applications.
  arXiv  Detail & Related papers  (2026-01-29T18:48:21Z)
• Note2Chat: Improving LLMs for Multi-Turn Clinical History Taking Using Medical Notes [17.99778043736069]
  We propose a note-driven framework that trains LLMs to conduct structured history taking and diagnosis by learning from medical notes.<n>We convert real-world medical notes into high-quality doctor-patient dialogues using a decision tree-guided generation and refinement pipeline.<n>We also propose a novel single-turn reasoning paradigm that reframes history taking as a sequence of single-turn reasoning problems.
  arXiv  Detail & Related papers  (2026-01-29T11:05:46Z)
• How to Train Private Clinical Language Models: A Comparative Study of Privacy-Preserving Pipelines for ICD-9 Coding [0.33148826359547523]
  Large language models trained on clinical text risk exposing sensitive patient information.<n>Despite rapid progress in DP optimisation, it remains unclear which privacy-preserving strategy actually works best.<n>Knowledge distillation from DP-trained teachers outperforms both direct DP-SGD and DP-synthetic data training.
  arXiv  Detail & Related papers  (2025-11-18T21:51:04Z)
• GAP: Graph-Assisted Prompts for Dialogue-based Medication Recommendation [16.144875467144917]
  We propose textbfGAP framework for dialogue-based medication recommendation.<n>It extracts medical concepts and corresponding states from dialogue to construct an explicitly patient-centric graph.<n>It can generate abundant queries and prompts, thus retrieving information from multiple sources to reduce the non-factual responses.
  arXiv  Detail & Related papers  (2025-05-19T09:18:19Z)
• Advancing Conversational Psychotherapy: Integrating Privacy, Dual-Memory, and Domain Expertise with Large Language Models [0.8563446809549775]
  Mental health has become a global issue that reveals the limitations of traditional conversational psychotherapy.<n>We introduce SoulSpeak, a Large Language Model (LLM)-enabled chatbots designed to democratize access to psychotherapy.
  arXiv  Detail & Related papers  (2024-12-04T03:02:46Z)
• Differential privacy enables fair and accurate AI-based analysis of speech disorders while protecting patient data [10.6135892856374]
  This study is the first to investigate differential privacy in pathological speech data.<n>It focuses on the trade-offs between privacy, diagnostic accuracy, and fairness.<n>Our results establish that DP can balance privacy and utility in speech disorder detection.
  arXiv  Detail & Related papers  (2024-09-27T18:25:54Z)
• RuleAlign: Making Large Language Models Better Physicians with Diagnostic Rule Alignment [54.91736546490813]
  We introduce the RuleAlign framework, designed to align Large Language Models with specific diagnostic rules. We develop a medical dialogue dataset comprising rule-based communications between patients and physicians. Experimental results demonstrate the effectiveness of the proposed approach.
  arXiv  Detail & Related papers  (2024-08-22T17:44:40Z)
• Dr-LLaVA: Visual Instruction Tuning with Symbolic Clinical Grounding [53.629132242389716]
  Vision-Language Models (VLM) can support clinicians by analyzing medical images and engaging in natural language interactions. VLMs often exhibit "hallucinogenic" behavior, generating textual outputs not grounded in contextual multimodal information. We propose a new alignment algorithm that uses symbolic representations of clinical reasoning to ground VLMs in medical knowledge.
  arXiv  Detail & Related papers  (2024-05-29T23:19:28Z)
• Confidential and Protected Disease Classifier using Fully Homomorphic Encryption [0.09424565541639365]
  Many users seek potential causes on platforms like ChatGPT or Bard before consulting a medical professional for their ailment. Despite the convenience of such platforms, sharing personal medical data online poses risks, including the presence of malicious platforms. We propose a novel framework combining FHE and Deep Learning for a secure and private diagnosis system.
  arXiv  Detail & Related papers  (2024-05-05T02:10:00Z)
• Towards Adapting Open-Source Large Language Models for Expert-Level Clinical Note Generation [19.08691249610632]
  This study presents a comprehensive domain- and task-specific adaptation process for the open-source LLaMA-2 13 billion parameter model.<n>Our process incorporates continued pretraining, supervised fine-tuning, and reinforcement learning from both AI and human feedback.<n>Our resulting model, LLaMA-Clinic, can generate clinical notes comparable in quality to those authored by physicians.
  arXiv  Detail & Related papers  (2024-04-25T15:34:53Z)
• Prompt-based Personalized Federated Learning for Medical Visual Question Answering [56.002377299811656]
  We present a novel prompt-based personalized federated learning (pFL) method to address data heterogeneity and privacy concerns. We regard medical datasets from different organs as clients and use pFL to train personalized transformer-based VQA models for each client.
  arXiv  Detail & Related papers  (2024-02-15T03:09:54Z)
• Benchmarking Large Language Models on Communicative Medical Coaching: a Novel System and Dataset [26.504409173684653]
  We introduce "ChatCoach", a human-AI cooperative framework designed to assist medical learners in practicing their communication skills during patient consultations. ChatCoachdifferentiates itself from conventional dialogue systems by offering a simulated environment where medical learners can practice dialogues with a patient agent, while a coach agent provides immediate, structured feedback. We have developed a dataset specifically for evaluating Large Language Models (LLMs) within the ChatCoach framework on communicative medical coaching tasks.
  arXiv  Detail & Related papers  (2024-02-08T10:32:06Z)
• Preserving privacy in domain transfer of medical AI models comes at no performance costs: The integral role of differential privacy [5.025818976218807]
  We evaluate the efficacy of DP-enhanced domain transfer (DP-DT) in diagnosing cardiomegaly, pleural effusion, pneumonia, atelectasis, and in identifying healthy subjects. Our results show that DP-DT, even with exceptionally high privacy levels, performs comparably to non-DP-DT.
  arXiv  Detail & Related papers  (2023-06-10T18:41:50Z)
• PlugMed: Improving Specificity in Patient-Centered Medical Dialogue Generation using In-Context Learning [20.437165038293426]
  The patient-centered medical dialogue systems strive to offer diagnostic interpretation services to users who are less knowledgeable about medical knowledge. It is difficult for the large language models (LLMs) to guarantee the specificity of responses in spite of its promising performance. Inspired by in-context learning, we propose PlugMed, a Plug-and-Play Medical Dialogue System.
  arXiv  Detail & Related papers  (2023-05-19T08:18:24Z)
• An Experimental Study on Private Aggregation of Teacher Ensemble Learning for End-to-End Speech Recognition [51.232523987916636]
  Differential privacy (DP) is one data protection avenue to safeguard user information used for training deep models by imposing noisy distortion on privacy data. In this work, we extend PATE learning to work with dynamic patterns, namely speech, and perform one very first experimental study on ASR to avoid acoustic data leakage.
  arXiv  Detail & Related papers  (2022-10-11T16:55:54Z)
• Semi-Supervised Variational Reasoning for Medical Dialogue Generation [70.838542865384]
  Two key characteristics are relevant for medical dialogue generation: patient states and physician actions. We propose an end-to-end variational reasoning approach to medical dialogue generation. A physician policy network composed of an action-classifier and two reasoning detectors is proposed for augmented reasoning ability.
  arXiv  Detail & Related papers  (2021-05-13T04:14:35Z)
• Privacy-preserving medical image analysis [53.4844489668116]
  We present PriMIA, a software framework designed for privacy-preserving machine learning (PPML) in medical imaging. We show significantly better classification performance of a securely aggregated federated learning model compared to human experts on unseen datasets. We empirically evaluate the framework's security against a gradient-based model inversion attack.
  arXiv  Detail & Related papers  (2020-12-10T13:56:00Z)
• MedDG: An Entity-Centric Medical Consultation Dataset for Entity-Aware Medical Dialogue Generation [86.38736781043109]
  We build and release a large-scale high-quality Medical Dialogue dataset related to 12 types of common Gastrointestinal diseases named MedDG. We propose two kinds of medical dialogue tasks based on MedDG dataset. One is the next entity prediction and the other is the doctor response generation. Experimental results show that the pre-train language models and other baselines struggle on both tasks with poor performance in our dataset.
  arXiv  Detail & Related papers  (2020-10-15T03:34:33Z)
• DeepEnroll: Patient-Trial Matching with Deep Embedding and Entailment Prediction [67.91606509226132]
  Clinical trials are essential for drug development but often suffer from expensive, inaccurate and insufficient patient recruitment. DeepEnroll is a cross-modal inference learning model to jointly encode enrollment criteria (tabular data) into a shared latent space for matching inference.
  arXiv  Detail & Related papers  (2020-01-22T17:51:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.