{"total":2007,"rows":[{"id":"2307.03109","title":"A Survey on Evaluation of Large Language Models","created":"2023-07-06","cited_by_count":1242,"area":null},{"id":"2008.02275","title":"Aligning AI With Shared Human Values","created":"2020-08-05","cited_by_count":723,"area":"alignment"},{"id":"2309.00770","title":"Bias and Fairness in Large Language Models: A Survey","created":"2023-09-02","cited_by_count":639,"area":null},{"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":"2108.04884","title":"Retiring Adult: New Datasets for Fair Machine Learning","created":"2021-08-10","cited_by_count":449,"area":null},{"id":"2108.13624","title":"Towards Out-Of-Distribution Generalization: A Survey","created":"2021-08-31","cited_by_count":436,"area":null},{"id":"2204.02937","title":"Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations","created":"2022-04-06","cited_by_count":381,"area":null},{"id":"2107.06917","title":"A Field Guide to Federated Optimization","created":"2021-07-14","cited_by_count":315,"area":null},{"id":"2109.13916","title":"Unsolved Problems in ML Safety","created":"2021-09-28","cited_by_count":292,"area":null},{"id":"2305.08283","title":"From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models","created":"2023-05-15","cited_by_count":260,"area":null},{"id":"2410.21819","title":"Self-Preference Bias in LLM-as-a-Judge","created":"2024-10-29","cited_by_count":258,"area":null},{"id":"2110.01167","title":"Trustworthy AI: From Principles to Practices","created":"2021-10-04","cited_by_count":207,"area":null},{"id":"2105.04054","title":"Societal Biases in Language Generation: Progress and Challenges","created":"2021-05-10","cited_by_count":202,"area":null},{"id":"2109.00725","title":"Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond","created":"2021-09-02","cited_by_count":178,"area":null},{"id":"2307.10616","title":"Heterogeneous Federated Learning: State-of-the-art and Research Challenges","created":"2023-07-20","cited_by_count":161,"area":null},{"id":"2110.00530","title":"A survey on datasets for fairness-aware machine learning","created":"2021-10-01","cited_by_count":157,"area":null},{"id":"2406.04244","title":"Benchmark Data Contamination of Large Language Models: A Survey","created":"2024-06-06","cited_by_count":147,"area":null},{"id":"2210.11369","title":"On Feature Learning in the Presence of Spurious Correlations","created":"2022-10-20","cited_by_count":145,"area":null},{"id":"2102.13186","title":"Towards a Unified Framework for Fair and Stable Graph Representation Learning","created":"2021-02-25","cited_by_count":128,"area":null},{"id":"2207.07068","title":"Bias Mitigation for Machine Learning Classifiers: A Comprehensive Survey","created":"2022-07-14","cited_by_count":125,"area":null},{"id":"2110.00857","title":"FairFed: Enabling Group Fairness in Federated Learning","created":"2021-10-02","cited_by_count":118,"area":null},{"id":"2202.02950","title":"Jury Learning: Integrating Dissenting Voices into Machine Learning Models","created":"2022-02-07","cited_by_count":118,"area":null},{"id":"2204.08570","title":"A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability","created":"2022-04-18","cited_by_count":118,"area":null},{"id":"2112.06409","title":"Data Collection and Quality Challenges in Deep Learning: A Data-Centric AI Perspective","created":"2021-12-13","cited_by_count":116,"area":null},{"id":"2103.06503","title":"Fair Mixup: Fairness via Interpolation","created":"2021-03-11","cited_by_count":109,"area":null},{"id":"2110.12884","title":"DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networks","created":"2021-10-25","cited_by_count":109,"area":null},{"id":"2201.12091","title":"Linear Adversarial Concept Erasure","created":"2022-01-28","cited_by_count":101,"area":null},{"id":"2106.00467","title":"A Clarification of the Nuances in the Fairness Metrics Landscape","created":"2021-06-01","cited_by_count":98,"area":null},{"id":"2102.00086","title":"Challenges in Automated Debiasing for Toxic Language Detection","created":"2021-01-29","cited_by_count":96,"area":null},{"id":"2105.12195","title":"Bias in Machine Learning Software: Why? How? What to do?","created":"2021-05-25","cited_by_count":93,"area":null},{"id":"2107.06641","title":"Trustworthy AI: A Computational Perspective","created":"2021-07-12","cited_by_count":93,"area":null},{"id":"2402.02680","title":"Large Language Models are Geographically Biased","created":"2024-02-05","cited_by_count":93,"area":"wm"},{"id":"2108.05233","title":"EDITS: Modeling and Mitigating Data Bias for Graph Neural Networks","created":"2021-08-11","cited_by_count":92,"area":null},{"id":"2211.13972","title":"Picking on the Same Person: Does Algorithmic Monoculture lead to Outcome Homogenization?","created":"2022-11-25","cited_by_count":91,"area":null},{"id":"2310.10076","title":"Verbosity Bias in Preference Labeling by Large Language Models","created":"2023-10-16","cited_by_count":91,"area":"alignment"},{"id":"2109.05433","title":"Are Gender-Neutral Queries Really Gender-Neutral? Mitigating Gender Bias in Image Search","created":"2021-09-12","cited_by_count":90,"area":null},{"id":"2201.06640","title":"Towards Adversarial Evaluations for Inexact Machine Unlearning","created":"2022-01-17","cited_by_count":84,"area":"safety"},{"id":"2106.14574","title":"Quantifying Social Biases in NLP: A Generalization and Empirical Comparison of Extrinsic Fairness Metrics","created":"2021-06-28","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":"2204.09888","title":"Fairness in Graph Mining: A Survey","created":"2022-04-21","cited_by_count":76,"area":null},{"id":"2104.10671","title":"User-oriented Fairness in Recommendation","created":"2021-04-21","cited_by_count":75,"area":null},{"id":"2103.01550","title":"Label-Imbalanced and Group-Sensitive Classification under Overparameterization","created":"2021-03-02","cited_by_count":74,"area":null},{"id":"2303.16626","title":"Fairlearn: Assessing and Improving Fairness of AI Systems","created":"2023-03-29","cited_by_count":74,"area":null},{"id":"2102.13004","title":"Towards Unbiased and Accurate Deferral to Multiple Experts","created":"2021-02-25","cited_by_count":72,"area":null},{"id":"2310.12560","title":"Fast Model Debias with Machine Unlearning","created":"2023-10-19","cited_by_count":72,"area":"safety"},{"id":"2203.16209","title":"Fair Contrastive Learning for Facial Attribute Classification","created":"2022-03-30","cited_by_count":71,"area":null},{"id":"2303.10431","title":"DeAR: Debiasing Vision-Language Models with Additive Residuals","created":"2023-03-18","cited_by_count":70,"area":"mllm"},{"id":"2402.17229","title":"Preserving Fairness Generalization in Deepfake Detection","created":"2024-02-27","cited_by_count":70,"area":null},{"id":"2104.14210","title":"FairDrop: Biased Edge Dropout for Enhancing Fairness in Graph Representation Learning","created":"2021-04-29","cited_by_count":68,"area":null},{"id":"2205.03257","title":"Synthetic Data -- what, why and how?","created":"2022-05-06","cited_by_count":67,"area":null},{"id":"2101.00352","title":"Characterizing Fairness Over the Set of Good Models Under Selective Labels","created":"2021-01-02","cited_by_count":65,"area":null},{"id":"2103.01907","title":"Fairness in Credit Scoring: Assessment, Implementation and Profit Implications","created":"2021-03-02","cited_by_count":65,"area":null},{"id":"2201.11706","title":"A Systematic Study of Bias Amplification","created":"2022-01-27","cited_by_count":65,"area":null},{"id":"2106.12674","title":"Fairness via Representation Neutralization","created":"2021-06-23","cited_by_count":63,"area":null},{"id":"2202.00126","title":"Handling Bias in Toxic Speech Detection: A Survey","created":"2022-01-26","cited_by_count":61,"area":null},{"id":"2106.04411","title":"Fair Feature Distillation for Visual Recognition","created":"2021-05-27","cited_by_count":59,"area":"distill"},{"id":"2203.02110","title":"FairPrune: Achieving Fairness Through Pruning for Dermatological Disease Diagnosis","created":"2022-03-04","cited_by_count":59,"area":null},{"id":"2205.04610","title":"Towards Intersectionality in Machine Learning: Including More Identities, Handling Underrepresentation, and Performing Evaluation","created":"2022-05-10","cited_by_count":59,"area":null},{"id":"2111.01872","title":"Towards Fairness-Aware Federated Learning","created":"2021-11-02","cited_by_count":58,"area":null},{"id":"2201.03662","title":"Learning Fair Node Representations with Graph Counterfactual Fairness","created":"2022-01-10","cited_by_count":58,"area":null},{"id":"2309.00035","title":"FACET: Fairness in Computer Vision Evaluation Benchmark","created":"2023-08-31","cited_by_count":58,"area":null},{"id":"2404.01349","title":"Fairness in Large Language Models: A Taxonomic Survey","created":"2024-03-31","cited_by_count":58,"area":null},{"id":"2106.12387","title":"Fairness in Cardiac MR Image Analysis: An Investigation of Bias Due to Data Imbalance in Deep Learning Based Segmentation","created":"2021-06-23","cited_by_count":57,"area":null},{"id":"2101.02032","title":"Socially Responsible AI Algorithms: Issues, Purposes, and Challenges","created":"2021-01-01","cited_by_count":56,"area":null},{"id":"2106.06142","title":"DORO: Distributional and Outlier Robust Optimization","created":"2021-06-11","cited_by_count":56,"area":null},{"id":"2105.06422","title":"Causally motivated Shortcut Removal Using Auxiliary Labels","created":"2021-05-13","cited_by_count":55,"area":null},{"id":"2205.14140","title":"CEBaB: Estimating the Causal Effects of Real-World Concepts on NLP Model Behavior","created":"2022-05-27","cited_by_count":55,"area":null},{"id":"2403.07857","title":"Fairness Feedback Loops: Training on Synthetic Data Amplifies Bias","created":"2024-03-12","cited_by_count":55,"area":null},{"id":"2102.12594","title":"Directional Bias Amplification","created":"2021-02-24","cited_by_count":54,"area":null},{"id":"2203.04913","title":"Leveling Down in Computer Vision: Pareto Inefficiencies in Fair Deep Classifiers","created":"2022-03-09","cited_by_count":53,"area":null},{"id":"2207.09239","title":"Assaying Out-Of-Distribution Generalization in Transfer Learning","created":"2022-07-19","cited_by_count":53,"area":null},{"id":"2310.16608","title":"Performative Prediction: Past and Future","created":"2023-10-25","cited_by_count":53,"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":"2312.12112","title":"Curated LLM: Synergy of LLMs and Data Curation for tabular augmentation in low-data regimes","created":"2023-12-19","cited_by_count":52,"area":null},{"id":"2211.01528","title":"Fair and Optimal Classification via Post-Processing","created":"2022-11-03","cited_by_count":51,"area":null},{"id":"2410.02584","title":"Towards Implicit Bias Detection and Mitigation in Multi-Agent LLM Interactions","created":"2024-10-03","cited_by_count":51,"area":"agents"},{"id":"2108.05921","title":"Hatemoji: A Test Suite and Adversarially-Generated Dataset for Benchmarking and Detecting Emoji-based Hate","created":"2021-08-12","cited_by_count":50,"area":null},{"id":"2108.08435","title":"Addressing Algorithmic Disparity and Performance Inconsistency in Federated Learning","created":"2021-08-19","cited_by_count":50,"area":null},{"id":"2108.08504","title":"Understanding and Mitigating Annotation Bias in Facial Expression Recognition","created":"2021-08-19","cited_by_count":50,"area":null},{"id":"2106.06054","title":"Fair Preprocessing: Towards Understanding Compositional Fairness of Data Transformers in Machine Learning Pipeline","created":"2021-06-02","cited_by_count":49,"area":null},{"id":"2201.01212","title":"AutoBalance: Optimized Loss Functions for Imbalanced Data","created":"2022-01-04","cited_by_count":49,"area":null},{"id":"2205.05256","title":"Evaluation Gaps in Machine Learning Practice","created":"2022-05-11","cited_by_count":49,"area":null},{"id":"2109.11429","title":"Robin Hood and Matthew Effects: Differential Privacy Has Disparate Impact on Synthetic Data","created":"2021-09-23","cited_by_count":48,"area":null},{"id":"2110.14222","title":"Sample Selection for Fair and Robust Training","created":"2021-10-27","cited_by_count":48,"area":null},{"id":"2202.05338","title":"Accountability in an Algorithmic Society: Relationality, Responsibility, and Robustness in Machine Learning","created":"2022-02-10","cited_by_count":48,"area":null},{"id":"2306.06123","title":"Adversarial attacks and defenses in explainable artificial intelligence: A survey","created":"2023-06-06","cited_by_count":48,"area":null},{"id":"2106.12705","title":"Alternative Microfoundations for Strategic Classification","created":"2021-06-24","cited_by_count":47,"area":null},{"id":"2202.08187","title":"Differential Privacy and Fairness in Decisions and Learning Tasks: A Survey","created":"2022-02-16","cited_by_count":47,"area":null},{"id":"2203.01584","title":"Fairness-aware Adversarial Perturbation Towards Bias Mitigation for Deployed Deep Models","created":"2022-03-03","cited_by_count":47,"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":"2306.09983","title":"Evaluating Superhuman Models with Consistency Checks","created":"2023-06-16","cited_by_count":47,"area":null},{"id":"2104.14556","title":"Discover the Unknown Biased Attribute of an Image Classifier","created":"2021-04-29","cited_by_count":46,"area":null},{"id":"2105.02317","title":"A Step Toward More Inclusive People Annotations for Fairness","created":"2021-05-05","cited_by_count":46,"area":null},{"id":"2101.04108","title":"Controllable Guarantees for Fair Outcomes via Contrastive Information Estimation","created":"2021-01-11","cited_by_count":45,"area":null},{"id":"2104.14537","title":"Towards Fair Classifiers Without Sensitive Attributes: Exploring Biases in Related Features","created":"2021-04-29","cited_by_count":45,"area":null},{"id":"2203.01255","title":"Low-Degree Multicalibration","created":"2022-03-02","cited_by_count":45,"area":null},{"id":"2101.06536","title":"Deep Cox Mixtures for Survival Regression","created":"2021-01-16","cited_by_count":44,"area":null},{"id":"2105.09989","title":"Multi-group Agnostic PAC Learnability","created":"2021-05-20","cited_by_count":44,"area":null},{"id":"2205.13574","title":"Pruning has a disparate impact on model accuracy","created":"2022-05-26","cited_by_count":44,"area":null},{"id":"2103.02735","title":"Fairness of Exposure in Stochastic Bandits","created":"2021-03-03","cited_by_count":43,"area":null}],"next_cursor":"100"}