spurious correlation

Attribution-Guided Model Rectification of Unreliable Neural Network Behaviors CVPR 2026 BERT, are you paying attention? Attention regularization with human-annotated rationales EACL 2026 Bridge: Basis-Driven Causal Inference Marries VFMs for Domain Generalization CVPR 2026 CaFlow: Enhancing Long-Term Action Quality Assessment with Causal Counterfactual Flow WACV 2026 Calibration vs Decision Making: Revisiting the Reliability Paradox in Unlearned Language Models ACL 2026 Causal Direct Preference Optimization for Language Model Alignment EACL 2026 Causal-HalBench: Uncovering LVLMs Object Hallucinations Through Causal Intervention AAAI 2026 CausalVAD: De-confounding End-to-End Autonomous Driving via Causal Intervention CVPR 2026 CIGMA: Causal Information-Gain Mechanistic Attribution of Attention Heads in Vision Transformers CVPR 2026 Concept-Guided Fine-Tuning: Steering ViTs away from Spurious Correlations to Improve Robustness CVPR 2026 Concept Regions Matter: Benchmarking CLIP with a New Cluster-Importance Approach CVPR 2026 COPO: Causal-Oriented Policy Optimization for Hallucinations of MLLMs CVPR 2026 DARC: Dual Adjustment Reasoning with Counterfactuals for Trustworthy Chest X-ray Classification CVPR 2026 Debiasing Logical Fallacy Detection for Real-World Robustness via Counterfactually Augmented Data ACL 2026 Domain Generalizing DINO for Visual Regression via Latent Distractor Subspace Consistency WACV 2026 Easy to Learn, Yet Hard to Forget: Towards Robust Unlearning Under Bias AAAI 2026 Image-based Outlier Synthesis With Training Data CVPR 2026 Learning from Synthetic Data via Provenance-Based Input Gradient Guidance CVPR 2026 Learning Invariant Modality Representation for Robust Multimodal Learning from a Causal Inference Perspective ACL 2026 Looking at Radiology Report Generation through a Causal Lens: A Survey ACL 2026 Lose Your Self (LoYS): An Adversarial Entropy-based Unsupervised Approach for Model Debiasing WACV 2026 LVLM-Aided Alignment of Task-Specific Vision Models CVPR 2026 Mitigating Error Amplification in Fast Adversarial Training CVPR 2026 Mitigating Multimodal Hallucinations via Gradient-based Self-Reflection CVPR 2026 Mitigating Spurious Correlations in Text Classification Using Latent Space Geometry ACL 2026