{"total":133,"rows":[{"id":"2107.09044","title":"Just Train Twice: Improving Group Robustness without Training Group Information","created":"2021-07-19","cited_by_count":523,"area":null},{"id":"2403.19647","title":"Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models","created":"2024-03-28","cited_by_count":435,"area":null},{"id":"2110.14503","title":"Simple data balancing achieves competitive worst-group-accuracy","created":"2021-10-27","cited_by_count":178,"area":null},{"id":"2107.01372","title":"Learning Debiased Representation via Disentangled Feature Augmentation","created":"2021-07-03","cited_by_count":116,"area":null},{"id":"2112.08313","title":"Measure and Improve Robustness in NLP Models: A Survey","created":"2021-12-15","cited_by_count":107,"area":null},{"id":"2103.02023","title":"EnD: Entangling and Disentangling deep representations for bias correction","created":"2021-03-02","cited_by_count":105,"area":null},{"id":"2204.02070","title":"Spread Spurious Attribute: Improving Worst-group Accuracy with Spurious Attribute Estimation","created":"2022-04-05","cited_by_count":88,"area":null},{"id":"2105.05612","title":"Evading the Simplicity Bias: Training a Diverse Set of Models Discovers Solutions with Superior OOD Generalization","created":"2021-05-12","cited_by_count":83,"area":null},{"id":"2206.14754","title":"Distilling Model Failures as Directions in Latent Space","created":"2022-06-29","cited_by_count":82,"area":null},{"id":"2106.02890","title":"Can Subnetwork Structure be the Key to Out-of-Distribution Generalization?","created":"2021-06-05","cited_by_count":75,"area":null},{"id":"2310.12560","title":"Fast Model Debias with Machine Unlearning","created":"2023-10-19","cited_by_count":72,"area":"safety"},{"id":"2108.10008","title":"BiaSwap: Removing dataset bias with bias-tailored swapping augmentation","created":"2021-08-23","cited_by_count":70,"area":null},{"id":"2202.04414","title":"Agree to Disagree: Diversity through Disagreement for Better Transferability","created":"2022-02-09","cited_by_count":70,"area":null},{"id":"2106.12674","title":"Fairness via Representation Neutralization","created":"2021-06-23","cited_by_count":63,"area":null},{"id":"2203.05818","title":"ZIN: When and How to Learn Invariance Without Environment Partition?","created":"2022-03-11","cited_by_count":58,"area":null},{"id":"2202.03418","title":"Diversify and Disambiguate: Learning From Underspecified Data","created":"2022-02-07","cited_by_count":56,"area":null},{"id":"2309.08534","title":"Towards Last-layer Retraining for Group Robustness with Fewer Annotations","created":"2023-09-15","cited_by_count":54,"area":null},{"id":"2203.12609","title":"Improving the Fairness of Chest X-ray Classifiers","created":"2022-03-23","cited_by_count":52,"area":null},{"id":"2206.10843","title":"Learning Debiased Classifier with Biased Committee","created":"2022-06-22","cited_by_count":51,"area":null},{"id":"2207.10077","title":"Discover and Mitigate Unknown Biases with Debiasing Alternate Networks","created":"2022-07-20","cited_by_count":47,"area":null},{"id":"2108.02943","title":"Unsupervised Learning of Debiased Representations with Pseudo-Attributes","created":"2021-08-06","cited_by_count":44,"area":null},{"id":"2301.09819","title":"Model Agnostic Sample Reweighting for Out-of-Distribution Learning","created":"2023-01-24","cited_by_count":44,"area":null},{"id":"2310.19035","title":"Does Invariant Graph Learning via Environment Augmentation Learn Invariance?","created":"2023-10-29","cited_by_count":42,"area":null},{"id":"2211.05568","title":"Unbiased Supervised Contrastive Learning","created":"2022-11-10","cited_by_count":40,"area":null},{"id":"2410.10855","title":"Core Knowledge Deficits in Multi-Modal Language Models","created":"2024-10-06","cited_by_count":38,"area":"mllm"},{"id":"2108.00049","title":"Object-aware Contrastive Learning for Debiased Scene Representation","created":"2021-07-30","cited_by_count":35,"area":null},{"id":"2203.15516","title":"Rich Feature Construction for the Optimization-Generalization Dilemma","created":"2022-03-24","cited_by_count":34,"area":null},{"id":"2108.05449","title":"Learning Bias-Invariant Representation by Cross-Sample Mutual Information Minimization","created":"2021-08-11","cited_by_count":32,"area":null},{"id":"2303.06167","title":"Overwriting Pretrained Bias with Finetuning Data","created":"2023-03-10","cited_by_count":32,"area":null},{"id":"2202.08926","title":"On Guiding Visual Attention with Language Specification","created":"2022-02-17","cited_by_count":30,"area":null},{"id":"2307.16851","title":"Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectives","created":"2023-07-31","cited_by_count":30,"area":"alignment"},{"id":"2301.13293","title":"Overcoming Simplicity Bias in Deep Networks using a Feature Sieve","created":"2023-01-30","cited_by_count":29,"area":null},{"id":"2309.16748","title":"Discovering environments with XRM","created":"2023-09-28","cited_by_count":26,"area":null},{"id":"2204.04384","title":"The Two Dimensions of Worst-case Training and the Integrated Effect for Out-of-domain Generalization","created":"2022-04-09","cited_by_count":21,"area":null},{"id":"2109.07258","title":"Federated Learning of Molecular Properties with Graph Neural Networks in a Heterogeneous Setting","created":"2021-09-15","cited_by_count":19,"area":null},{"id":"2112.14380","title":"Cross-Domain Empirical Risk Minimization for Unbiased Long-tailed Classification","created":"2021-12-29","cited_by_count":19,"area":null},{"id":"2205.14594","title":"Revisiting the Importance of Amplifying Bias for Debiasing","created":"2022-05-29","cited_by_count":19,"area":null},{"id":"2402.18919","title":"Decompose-and-Compose: A Compositional Approach to Mitigating Spurious Correlation","created":"2024-02-29","cited_by_count":18,"area":null},{"id":"2211.15231","title":"Chroma-VAE: Mitigating Shortcut Learning with Generative Classifiers","created":"2022-11-28","cited_by_count":17,"area":null},{"id":"2204.13749","title":"Learning to Split for Automatic Bias Detection","created":"2022-04-28","cited_by_count":16,"area":null},{"id":"2303.01687","title":"Differentially Private Neural Tangent Kernels for Privacy-Preserving Data Generation","created":"2023-03-03","cited_by_count":15,"area":null},{"id":"2104.00170","title":"Are Bias Mitigation Techniques for Deep Learning Effective?","created":"2021-04-01","cited_by_count":14,"area":null},{"id":"2111.03740","title":"Toward Learning Human-aligned Cross-domain Robust Models by Countering Misaligned Features","created":"2021-11-05","cited_by_count":14,"area":null},{"id":"2201.11259","title":"Controlling Directions Orthogonal to a Classifier","created":"2022-01-27","cited_by_count":13,"area":null},{"id":"2212.02648","title":"Spuriosity Rankings: Sorting Data to Measure and Mitigate Biases","created":"2022-12-05","cited_by_count":13,"area":null},{"id":"2308.00994","title":"SYNAuG: Exploiting Synthetic Data for Data Imbalance Problems","created":"2023-08-02","cited_by_count":13,"area":null},{"id":"2311.01573","title":"Improving Fairness using Vision-Language Driven Image Augmentation","created":"2023-11-02","cited_by_count":13,"area":null},{"id":"2204.02426","title":"OccamNets: Mitigating Dataset Bias by Favoring Simpler Hypotheses","created":"2022-04-05","cited_by_count":11,"area":null},{"id":"2504.07092","title":"Are We Done with Object-Centric Learning?","created":"2025-04-09","cited_by_count":11,"area":null},{"id":"2302.05441","title":"Project and Probe: Sample-Efficient Domain Adaptation by Interpolating Orthogonal Features","created":"2023-02-10","cited_by_count":10,"area":null},{"id":"2112.01021","title":"Fighting Fire with Fire: Contrastive Debiasing without Bias-free Data via Generative Bias-transformation","created":"2021-12-02","cited_by_count":9,"area":null},{"id":"2203.05877","title":"A Sentence is Worth 128 Pseudo Tokens: A Semantic-Aware Contrastive Learning Framework for Sentence Embeddings","created":"2022-03-11","cited_by_count":9,"area":null},{"id":"2312.02615","title":"Projection Regret: Reducing Background Bias for Novelty Detection via Diffusion Models","created":"2023-12-05","cited_by_count":9,"area":"diffusion"},{"id":"2111.13108","title":"Combating Unknown Bias with Effective Bias-Conflicting Scoring and Gradient Alignment","created":"2021-11-25","cited_by_count":8,"area":null},{"id":"2102.06406","title":"A Too-Good-to-be-True Prior to Reduce Shortcut Reliance","created":"2021-02-12","cited_by_count":7,"area":null},{"id":"2310.06161","title":"Mitigating Simplicity Bias in Deep Learning for Improved OOD Generalization and Robustness","created":"2023-10-09","cited_by_count":7,"area":null},{"id":"2404.05579","title":"DRoP: Distributionally Robust Data Pruning","created":"2024-04-08","cited_by_count":7,"area":null},{"id":"2512.23461","title":"Eliminating Inductive Bias in Reward Models with Information-Theoretic Guidance","created":"2025-12-29","cited_by_count":7,"area":"alignment"},{"id":"2106.07847","title":"Learning Stable Classifiers by Transferring Unstable Features","created":"2021-06-15","cited_by_count":6,"area":null},{"id":"2208.03462","title":"Class Is Invariant to Context and Vice Versa: On Learning Invariance for Out-Of-Distribution Generalization","created":"2022-08-06","cited_by_count":6,"area":null},{"id":"2409.03303","title":"Improving Robustness to Multiple Spurious Correlations by Multi-Objective Optimization","created":"2024-09-05","cited_by_count":6,"area":null},{"id":"2503.17226","title":"DDB: Diffusion Driven Balancing to Address Spurious Correlations","created":"2025-03-21","cited_by_count":6,"area":"diffusion"},{"id":"2211.08722","title":"Learning with Noisy Labels over Imbalanced Subpopulations","created":"2022-11-16","cited_by_count":5,"area":null},{"id":"2306.11120","title":"Confidence-Based Model Selection: When to Take Shortcuts for Subpopulation Shifts","created":"2023-06-19","cited_by_count":5,"area":null},{"id":"2505.14449","title":"Mitigating Subgroup Disparities in Multi-Label Speech Emotion Recognition: A Pseudo-Labeling and Unsupervised Learning Approach","created":"2025-05-20","cited_by_count":5,"area":null},{"id":"2106.07916","title":"Encouraging Intra-Class Diversity Through a Reverse Contrastive Loss for Better Single-Source Domain Generalization","created":"2021-06-15","cited_by_count":4,"area":null},{"id":"2210.00891","title":"Information Removal at the bottleneck in Deep Neural Networks","created":"2022-09-30","cited_by_count":4,"area":null},{"id":"2306.11957","title":"Challenges and Opportunities in Improving Worst-Group Generalization in Presence of Spurious Features","created":"2023-06-21","cited_by_count":4,"area":null},{"id":"2404.19250","title":"Enhancing Intrinsic Features for Debiasing via Investigating Class-Discerning Common Attributes in Bias-Contrastive Pair","created":"2024-04-30","cited_by_count":4,"area":null},{"id":"2501.18277","title":"Sebra: Debiasing Through Self-Guided Bias Ranking","created":"2025-01-30","cited_by_count":4,"area":null},{"id":"2507.11690","title":"The Impact of Coreset Selection on Spurious Correlations and Group Robustness","created":"2025-07-15","cited_by_count":4,"area":null},{"id":"2104.10553","title":"Rethinking Annotation Granularity for Overcoming Shortcuts in Deep Learning-based Radiograph Diagnosis: A Multicenter Study","created":"2021-04-21","cited_by_count":3,"area":null},{"id":"2108.10549","title":"StyleAugment: Learning Texture De-biased Representations by Style Augmentation without Pre-defined Textures","created":"2021-08-24","cited_by_count":3,"area":null},{"id":"2301.03844","title":"Look Beyond Bias with Entropic Adversarial Data Augmentation","created":"2023-01-10","cited_by_count":3,"area":null},{"id":"2302.01385","title":"Hyper-parameter Tuning for Fair Classification without Sensitive Attribute Access","created":"2023-02-02","cited_by_count":3,"area":null},{"id":"2312.04893","title":"Annotation-Free Group Robustness via Loss-Based Resampling","created":"2023-12-08","cited_by_count":3,"area":null},{"id":"2405.15661","title":"Exposing Image Classifier Shortcuts with Counterfactual Frequency (CoF) Tables","created":"2024-05-24","cited_by_count":3,"area":null},{"id":"2410.14315","title":"Optimizing importance weighting in the presence of sub-population shifts","created":"2024-10-18","cited_by_count":3,"area":null},{"id":"2411.19623","title":"FairDD: Fair Dataset Distillation","created":"2024-11-29","cited_by_count":3,"area":null},{"id":"2506.04652","title":"EMO-Debias: Benchmarking Gender Debiasing Techniques in Multi-Label Speech Emotion Recognition","created":"2025-06-05","cited_by_count":3,"area":null},{"id":"2202.10943","title":"Gradient Based Activations for Accurate Bias-Free Learning","created":"2022-02-17","cited_by_count":2,"area":null},{"id":"2202.11811","title":"NeuroView-RNN: It's About Time","created":"2022-02-23","cited_by_count":2,"area":null},{"id":"2204.09583","title":"Improved Group Robustness via Classifier Retraining on Independent Splits","created":"2022-04-20","cited_by_count":2,"area":null},{"id":"2204.12941","title":"Unsupervised Learning of Unbiased Visual Representations","created":"2022-04-26","cited_by_count":2,"area":null},{"id":"2207.10018","title":"Mitigating Algorithmic Bias with Limited Annotations","created":"2022-07-20","cited_by_count":2,"area":null},{"id":"2305.12123","title":"Modeling the Q-Diversity in a Min-max Play Game for Robust Optimization","created":"2023-05-20","cited_by_count":2,"area":null},{"id":"2310.06588","title":"FTFT: Efficient and Robust Fine-Tuning by Transferring Training Dynamics","created":"2023-10-10","cited_by_count":2,"area":null},{"id":"2312.08288","title":"Hybrid Sample Synthesis-based Debiasing of Classifier in Limited Data Setting","created":"2023-12-13","cited_by_count":2,"area":null},{"id":"2406.02889","title":"Language-guided Detection and Mitigation of Unknown Dataset Bias","created":"2024-06-05","cited_by_count":2,"area":null},{"id":"2409.02792","title":"UnLearning from Experience to Avoid Spurious Correlations","created":"2024-09-04","cited_by_count":2,"area":"safety"},{"id":"2505.22829","title":"Bridging Distribution Shift and AI Safety: Conceptual and Methodological Synergies","created":"2025-05-28","cited_by_count":2,"area":null},{"id":"2506.02294","title":"Improving Knowledge Distillation Under Unknown Covariate Shift Through Confidence-Guided Data Augmentation","created":"2025-06-02","cited_by_count":2,"area":"distill"},{"id":"2507.17748","title":"Large Learning Rates Simultaneously Achieve Robustness to Spurious Correlations and Compressibility","created":"2025-07-23","cited_by_count":2,"area":null},{"id":"2603.07323","title":"Norm-Hierarchy Transitions in Representation Learning: When and Why Neural Networks Abandon Shortcuts","created":"2026-03-07","cited_by_count":2,"area":null},{"id":"2603.20899","title":"Mitigating Shortcut Reasoning in Language Models: A Gradient-Aware Training Approach","created":"2026-03-21","cited_by_count":2,"area":"lr"},{"id":"2109.04834","title":"An Evaluation Dataset and Strategy for Building Robust Multi-turn Response Selection Model","created":"2021-09-10","cited_by_count":1,"area":null},{"id":"2110.07778","title":"NeuroView: Explainable Deep Network Decision Making","created":"2021-10-15","cited_by_count":1,"area":null},{"id":"2206.03680","title":"Improving Evaluation of Debiasing in Image Classification","created":"2022-06-08","cited_by_count":1,"area":null},{"id":"2208.08017","title":"Towards Generating Robust, Fair, and Emotion-Aware Explanations for Recommender Systems","created":"2022-08-17","cited_by_count":1,"area":null},{"id":"2210.12195","title":"Just Mix Once: Worst-group Generalization by Group Interpolation","created":"2022-10-21","cited_by_count":1,"area":null}],"next_cursor":"100"}