conftrace_

out-of-domain performance

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

instance difficulty analysis (1) user interface agent (1) weighted accuracy (1) kendall correlation (1) user interface control (1) instance difficulty (1) large language model (1) evaluation dataset (1) dataset quality (1) counterfactual augmentation (1)

Papers

CATfOOD: Counterfactual Augmented Training for Improving Out-of-Domain Performance and Calibration EACL 2024 On the Effects of Data Scale on UI Control Agents NeurIPS 2024 ILDAE: Instance-Level Difficulty Analysis of Evaluation Data ACL 2022