Schroedinger's Threshold: When the AUC doesn't predict Accuracy

4 April 2024

Papers citing "Schroedinger's Threshold: When the AUC doesn't predict Accuracy"

2 / 2 papers shown

Title
Evaluating Attribution in Dialogue Systems: The BEGIN Benchmark Nouha Dziri Hannah Rashkin Tal Linzen David Reitter ALM 195 79 0 30 Apr 2021
Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metrics Artidoro Pagnoni Vidhisha Balachandran Yulia Tsvetkov HILM 231 305 0 27 Apr 2021