Hi, thanks for releasing this project!
I was able to generate the task index and reasoning data, but I still don’t understand how to evaluate a model on EHR-Bench.
I cannot find a clear evaluation script or example command in the repo.
Could you explain the evaluation process or provide a minimal example?
Thank you!
Hi, thanks for releasing this project!
I was able to generate the task index and reasoning data, but I still don’t understand how to evaluate a model on EHR-Bench.
I cannot find a clear evaluation script or example command in the repo.
Could you explain the evaluation process or provide a minimal example?
Thank you!