{"type":"ScholarlyArticle","title":"Improving Group Robustness on Spurious Correlation via Evidential Alignment (Extended Abstract)","authors":[{"name":"Wenqian Ye","slug":"wenqian-ye","given":"Wenqian","family":"Ye","affiliation":""},{"name":"Guangtao Zheng","slug":"guangtao-zheng","given":"Guangtao","family":"Zheng","affiliation":""},{"name":"Aidong Zhang","slug":"aidong-zhang","given":"Aidong","family":"Zhang","affiliation":""}],"abstract":"Deep neural networks often rely on spurious correlations, i.e., superficial associations between non-causal features and prediction targets. While yielding high overall accuracy during training, such reliance degrades generalization on minority groups where these correlations break down. Existing methods mitigate this issue by using external group annotations or auxiliary deterministic models, but group annotations are costly to obtain and deterministic auxiliaries may fail to capture the full spectrum of biases learned by the model. We propose Evidential Alignment, a framework that leverages uncertainty quantification to identify and suppress spurious correlations without requiring group annotations. By transforming a biased ERM model from first-order to second-order risk minimization with a Dirichlet distribution and applying an evidential calibration step that reweighs samples by their epistemic uncertainty, Evidential Alignment debiases the model while preserving core features. We provide theoretical guarantees and demonstrate strong worst-group accuracy across diverse architectures and modalities.","doi":"10.24963/ijcai.2026/929","url":"https://ijcai.org/proceedings/2026/929","pdf":"https://ijcai.org/proceedings/2026/0929.pdf","markdown":"https://ijcai.org/proceedings/2026/929.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/929","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Sister Conferences Best Papers","track":"Sister Conferences Best Papers","number":929,"pages":{"first":8295,"last":8300},"keywords":["Uncertainty in AI: Uncertainty representations","Machine Learning: Robustness"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}