Kejia Chen
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper proposes mitigating the progressive degradation of safety in language models caused by many-shot jailbreak attacks by appending a single, fixed safety demonstration at inference time.
A large language model-based chatbot improved patient visit preparation and satisfaction.
Papers
A prospective randomized study of patient-centered AI for clinical visit preparation
Xincheng Tan, Matthew Thompson, Xiang Ji, Angelica Willis +32 more
A large language model-based chatbot improved patient visit preparation and satisfaction.