{"total":18,"rows":[{"id":"2603.00028","title":"EPPCMinerBen: A Novel Benchmark for Evaluating Large Language Models on Electronic Patient-Provider Communication via the Patient Portal","created":"2026-02-04","cited_by_count":4,"area":null},{"id":"2603.29373","title":"Beyond Idealized Patients: Evaluating LLMs under Challenging Patient Behaviors in Medical Consultations","created":"2026-03-31","cited_by_count":3,"area":null},{"id":"2603.05776","title":"PVminerLLM: Structured Extraction of Patient Voice from Patient-Generated Text using Large Language Models","created":"2026-03-06","cited_by_count":2,"area":null},{"id":"2604.07549","title":"EMSDialog: Synthetic Multi-person Emergency Medical Service Dialogue Generation from Electronic Patient Care Reports via Multi-LLM Agents","created":"2026-04-08","cited_by_count":2,"area":null},{"id":"2604.09737","title":"STaR-DRO: Stateful Tsallis Reweighting for Group-Robust Structured Prediction","created":"2026-04-09","cited_by_count":2,"area":null},{"id":"2601.08690","title":"All Required, In Order: Phase-Level Evaluation for AI-Human Dialogue in Healthcare and Beyond","created":"2026-01-13","cited_by_count":1,"area":null},{"id":"2601.21551","title":"Note2Chat: Improving LLMs for Multi-Turn Clinical History Taking Using Medical Notes","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2603.24132","title":"MedAidDialog: A Multilingual Multi-Turn Medical Dialogue Dataset for Accessible Healthcare","created":"2026-03-25","cited_by_count":1,"area":null},{"id":"2604.15588","title":"\"Excuse me, may I say something...\" CoLabScience, A Proactive AI Assistant for Biomedical Discovery and LLM-Expert Collaborations","created":"2026-04-16","cited_by_count":1,"area":null},{"id":"2508.19077","title":"\"Where does it hurt?\" -- Dataset and Study on Physician Intent Trajectories in Doctor Patient Dialogues","created":"2025-08-26","cited_by_count":0,"area":null},{"id":"2511.00514","title":"Fine-Tuning DialoGPT on Common Diseases in Rural Nepal for Medical Conversations","created":"2025-11-01","cited_by_count":0,"area":null},{"id":"2601.15645","title":"Towards Reliable Medical LLMs: Benchmarking and Enhancing Confidence Estimation of Large Language Models in Medical Consultation","created":"2026-01-22","cited_by_count":0,"area":null},{"id":"2605.13292","title":"IndicMedDialog: A Parallel Multi-Turn Medical Dialogue Dataset for Accessible Healthcare in Indic Languages","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.28170","title":"Localizing Input Uncertainty Quantification for Large Language Models via Shapley Values","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2607.09142","title":"MedRealMM: A Real-World Multimodal Benchmark for Chinese Online Medical Consultation","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2608.09024","title":"ELICITED: EHR-grounded Longitudinal Interactive Conversations for Information-seeking Triage Evaluation and Decision-making","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.24621","title":"Beyond Semantic Accuracy: Consequence-Aware Evaluation for Safety-Critical Language Understanding","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2608.27110","title":"DocTalkBN: A Novel Dataset of Expert Telemedicine Conversations in Bengali","created":"2026-08-27","cited_by_count":0,"area":null}],"next_cursor":null}