Debiasing Without Annotations: Cross-View Consensus Boosts Worst-Group Accuracy

Weiwei Li · hf · 2026-11-19

Researchers from UESTC and Sichuan University propose a multi-view debiasing method that aggregates within-class partitions across diverse representation spaces to reduce reliance on spurious correlations. Unlike prior approaches requiring costly human-annotated bias attributes—which may not match the shortcuts models actually use—this cross-view consensus approach improves worst-group accuracy without any bias supervision.

Original post →

More from Research

Research channel →