Yang Tan

MedChatZH: a Better Medical Adviser Learns from Better Instructions

2023 · arXiv (Cornell University)

Generative large language models (LLMs) have shown great success in various applications, including question-answering (QA) and dialogue systems. However, in specialized domains like traditional Chinese medical QA, these models may perform unsatisfactorily without fine-tuning on …

Practice of FATE: Performance Improving Techniques

2023

Federated Learning is a type of privacy-preserving machine learning technology, which enables different parties to build a common, robust machine learning model together without sharing private data.