FAD Curve Analysis
1 papers with code • 0 benchmarks • 0 datasets
Feature Attribution Dropping (FAD) curve analysis is a performance plot and evaluation metric for feature attribution methods: FAD curve and its Normalized Area Under the Curve (N-AUC).
Benchmarks
These leaderboards are used to track progress in FAD Curve Analysis
Most implemented papers
Doctor XAvIer: Explainable Diagnosis on Physician-Patient Dialogues and XAI Evaluation
hillary-ngai/doctor_xavier
•
•
BioNLP (ACL) 2022
We introduce Doctor XAvIer, a BERT-based diagnostic system that extracts relevant clinical data from transcribed patient-doctor dialogues and explains predictions using feature attribution methods.
