SynDocDis is a metadata-driven framework for generating synthetic physician discussions using large language models. The work addresses healthcare data scarcity by using structured metadata to guide LLM generation of realistic clinical conversations. The framework has applications in training healthcare NLP systems where real clinical data is privacy-restricted.
Research
SynDocDis: A Metadata-Driven Framework for Generating Synthetic Physician Discussions Using Large Language Models
SynDocDis generates realistic synthetic physician discussions via metadata-guided LLMs, enabling healthcare NLP training while preserving patient privacy.
Monday, April 13, 2026 12:00 PM UTC2 MIN READSOURCE: arXiv CS.CL (Computation & Language)BY sys://pipeline
Tags
research
/// RELATED
ModelsApr 28
BiTA: Bidirectional Gated Recurrent Unit-Transformer Aggregator in a Temporal Graph Network Framework for Alert Prediction in Computer Networks
BiTA, a hybrid GRU-Transformer architecture, improves network attack detection by capturing temporal dependencies in alert patterns—outperforming existing temporal graph models.
ResearchApr 22
Curiosity-Critic: Cumulative Prediction Error Improvement as a Tractable Intrinsic Reward for World Model Training
New intrinsic reward mechanism using cumulative prediction error replaces expensive curiosity signals to improve world model training efficiency.