3 papers
cs.CL2024
SYNFAC-EDIT: Synthetic Imitation Edit Feedback for Factual Alignment in Clinical Summarization
Prakamya Mishra, Zonghai Yao, Parth Vashisht +4
Large Language Models (LLMs) such as GPT & Llama have demonstrated significant achievements in summarization tasks but struggle with factual inaccuracies, a critical issue in clini…
cs.CL2023
Synthetic Imitation Edit Feedback for Factual Alignment in Clinical Summarization
Prakamya Mishra, Zonghai Yao, Shuwei Chen +3
Large Language Models (LLMs) like the GPT and LLaMA families have demonstrated exceptional capabilities in capturing and condensing critical contextual information and achieving st…
cs.CL2023
Do Physicians Know How to Prompt? The Need for Automatic Prompt Optimization Help in Clinical Note Generation
Zonghai Yao, Ahmed Jaafar, Beining Wang +2
This study examines the effect of prompt engineering on the performance of Large Language Models (LLMs) in clinical note generation. We introduce an Automatic Prompt Optimization (…