2 papers
cs.CL2026
In-Domain Supervised Pathology Report Classification: A Reproducible Pipeline from Data Curation to Production-Matched Evaluation
Isaac Hands, Bin Huang, Adam Spannaus +4
We introduce an in-domain supervised pipeline designed to counter the out-of-distribution performance drop that hampers supervised biomedical NLP models, a problem observed when mo…
cs.LG2025
Global explainability of a deep abstaining classifier
Sayera Dhaubhadel, Jamaludin Mohd-Yusof, Benjamin H. McMahon +8
We present a global explainability method to characterize sources of errors in the histology prediction task of our real-world multitask convolutional neural network (MTCNN)-based…