A Data-Centric Approach To Generate Faithful and High Quality Patient Summaries with Large Language Models

arXiv:2402.15422v1 Announce Type: cross
Abstract: Patients often face difficulties in understanding their hospitalizations, while healthcare workers have limited resources to provide explanations. In this work, we investigate the potential of large language models to generate patient summaries based on doctors' notes and study the effect of training data on the faithfulness and quality of the generated summaries. To this end, we develop a rigorous labeling protocol for hallucinations, and have two medical experts annotate 100 real-world summaries and 100 generated …

abstract arxiv cs.ai cs.cl cs.lg data data-centric doctors face generate healthcare language language models large language large language models notes patient patients quality resources study type understanding work workers