Is your benchmark truly adversarial? AdvScore: Evaluating Human-Grounded Adversarialness Paper โข 2406.16342 โข Published Jun 24, 2024
Do great minds think alike? Investigating Human-AI Complementarity in Question Answering with CAIMIRA Paper โข 2410.06524 โข Published Oct 9, 2024 โข 4
MATE: Multi-view Attention for Table Transformer Efficiency Paper โข 2109.04312 โข Published Sep 9, 2021
Toward Deconfounding the Influence of Entity Demographics for Question Answering Accuracy Paper โข 2104.07571 โข Published Apr 15, 2021