Stanford-AIMI/GREEN
a radiology report generation metric that leverages the natural language understanding of language models to identify and explain clinically significant errors in candidate reports
Python
Issues
- 2
pip install downloads different files
#9 opened by johannes2moll - 2
- 1
Training Data
#8 opened by HuichiZhou - 2
demo doesn't work: No module named 'utils'
#3 opened by JunMa11 - 2
Summary issue : Model responses don't always include all errors categories causing crash
#6 opened by rkassana - 2
Plan for releasing other models
#1 opened by wjhou