Cumulative Meta-Learning from Active Learning Queries for Robustness to Spurious Correlations

ArXi:2605.20771v1 Announce Type: new Spurious correlations in real-world datasets cause machine learning models to rely on irrelevant patterns, undermining reliability, generalization, and fairness. Active learning offers a promising way to address this failure mode by querying informative samples that distinguish core features from spurious ones. However, standard active-learning methods simply append queried examples to the labeled set, effectively updating only the likelihood term.