{"total":170,"rows":[{"id":"2306.03819","title":"LEACE: Perfect linear concept erasure in closed form","created":"2023-06-06","cited_by_count":267,"area":null},{"id":"2101.09523","title":"Debiasing Pre-trained Contextualised Embeddings","created":"2021-01-23","cited_by_count":107,"area":null},{"id":"2203.11933","title":"A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learning","created":"2022-03-22","cited_by_count":104,"area":"mllm"},{"id":"2201.12091","title":"Linear Adversarial Concept Erasure","created":"2022-01-28","cited_by_count":101,"area":null},{"id":"2202.00443","title":"The Text Anonymization Benchmark (TAB): A Dedicated Corpus and Evaluation Framework for Text Anonymization","created":"2022-01-25","cited_by_count":95,"area":null},{"id":"2308.10149","title":"A Survey on Fairness in Large Language Models","created":"2023-08-20","cited_by_count":95,"area":null},{"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":"2112.06598","title":"WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models","created":"2021-12-13","cited_by_count":89,"area":null},{"id":"2112.14168","title":"A Survey on Gender Bias in Natural Language Processing","created":"2021-12-28","cited_by_count":89,"area":null},{"id":"2106.01221","title":"Differential Privacy for Text Analytics via Natural Text Sanitization","created":"2021-06-02","cited_by_count":77,"area":null},{"id":"2106.11410","title":"A Survey of Race, Racism, and Anti-Racism in NLP","created":"2021-06-21","cited_by_count":75,"area":null},{"id":"2308.00755","title":"The Bias Amplification Paradox in Text-to-Image Generation","created":"2023-08-01","cited_by_count":70,"area":null},{"id":"2309.06746","title":"DP-Forward: Fine-tuning and Inference on Language Models with Differential Privacy in Forward Pass","created":"2023-09-13","cited_by_count":67,"area":"safety"},{"id":"2106.12674","title":"Fairness via Representation Neutralization","created":"2021-06-23","cited_by_count":63,"area":null},{"id":"2203.02110","title":"FairPrune: Achieving Fairness Through Pruning for Dermatological Disease Diagnosis","created":"2022-03-04","cited_by_count":59,"area":null},{"id":"2203.09192","title":"Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists","created":"2022-03-17","cited_by_count":55,"area":null},{"id":"2106.05469","title":"Variational Information Bottleneck for Effective Low-Resource Fine-Tuning","created":"2021-06-10","cited_by_count":51,"area":null},{"id":"2402.09631","title":"Representation Surgery: Theory and Practice of Affine Steering","created":"2024-02-15","cited_by_count":50,"area":null},{"id":"2203.07228","title":"FairLex: A Multilingual Benchmark for Evaluating Fairness in Legal Text Processing","created":"2022-03-14","cited_by_count":49,"area":null},{"id":"2101.10001","title":"Diverse Adversaries for Mitigating Bias in Training","created":"2021-01-25","cited_by_count":48,"area":null},{"id":"2207.04153","title":"Probing Classifiers are Unreliable for Concept Removal and Detection","created":"2022-07-08","cited_by_count":41,"area":null},{"id":"2105.09829","title":"Personalized Counterfactual Fairness in Recommendation","created":"2021-05-20","cited_by_count":38,"area":null},{"id":"2106.05937","title":"Fair Normalizing Flows","created":"2021-06-10","cited_by_count":38,"area":null},{"id":"2105.02685","title":"A Novel Estimator of Mutual Information for Learning to Disentangle Textual Representations","created":"2021-05-06","cited_by_count":37,"area":null},{"id":"2105.15164","title":"DISSECT: Disentangled Simultaneous Explanations via Concept Traversals","created":"2021-05-31","cited_by_count":37,"area":null},{"id":"2102.04140","title":"Quantifying and Mitigating Privacy Risks of Contrastive Learning","created":"2021-02-08","cited_by_count":36,"area":"safety"},{"id":"2104.13640","title":"Societal Biases in Retrieved Contents: Measurement Framework and Adversarial Mitigation for BERT Rankers","created":"2021-04-28","cited_by_count":35,"area":null},{"id":"2109.08253","title":"Balancing out Bias: Achieving Fairness Through Balanced Training","created":"2021-09-16","cited_by_count":34,"area":null},{"id":"2109.10645","title":"Contrastive Learning for Fair Representations","created":"2021-09-22","cited_by_count":34,"area":null},{"id":"2203.07893","title":"Gold Doesn't Always Glitter: Spectral Removal of Linear and Nonlinear Guarded Attribute Information","created":"2022-03-15","cited_by_count":34,"area":null},{"id":"2210.11471","title":"Choose Your Lenses: Flaws in Gender Bias Evaluation","created":"2022-10-20","cited_by_count":29,"area":null},{"id":"2110.03212","title":"Influence Tuning: Demoting Spurious Correlations via Instance Attribution and Instance-Driven Updates","created":"2021-10-07","cited_by_count":27,"area":null},{"id":"2205.13619","title":"Fairness in Recommendation: Foundations, Methods and Applications","created":"2022-05-26","cited_by_count":27,"area":null},{"id":"2310.11958","title":"Emptying the Ocean with a Spoon: Should We Edit Models?","created":"2023-10-18","cited_by_count":27,"area":null},{"id":"2309.14381","title":"Survey of Social Bias in Vision-Language Models","created":"2023-09-24","cited_by_count":26,"area":"mllm"},{"id":"2302.06321","title":"Parameter-efficient Modularised Bias Mitigation via AdapterFusion","created":"2023-02-13","cited_by_count":25,"area":null},{"id":"2305.10204","title":"Shielded Representations: Protecting Sensitive Attributes Through Iterative Gradient-Based Projection","created":"2023-05-17","cited_by_count":25,"area":null},{"id":"2101.09525","title":"Dictionary-based Debiasing of Pre-trained Word Embeddings","created":"2021-01-23","cited_by_count":24,"area":null},{"id":"2206.03200","title":"FairVFL: A Fair Vertical Federated Learning Framework with Contrastive Adversarial Learning","created":"2022-06-07","cited_by_count":23,"area":null},{"id":"2205.02393","title":"Optimising Equal Opportunity Fairness in Model Training","created":"2022-05-05","cited_by_count":22,"area":null},{"id":"2208.10013","title":"FairDisCo: Fairer AI in Dermatology via Disentanglement Contrastive Learning","created":"2022-08-22","cited_by_count":22,"area":null},{"id":"2212.10563","title":"BLIND: Bias Removal With No Demographics","created":"2022-12-20","cited_by_count":22,"area":null},{"id":"2204.02567","title":"FairNeuron: Improving Deep Neural Network Fairness with Adversary Games on Selective Neurons","created":"2022-04-06","cited_by_count":21,"area":null},{"id":"2210.07213","title":"FARE: Provably Fair Representation Learning with Practical Certificates","created":"2022-10-13","cited_by_count":21,"area":null},{"id":"2202.06618","title":"A Differential Entropy Estimator for Training Neural Networks","created":"2022-02-14","cited_by_count":20,"area":null},{"id":"2206.04500","title":"Unlearning Protected User Attributes in Recommendations with Adversarial Training","created":"2022-06-09","cited_by_count":20,"area":"safety"},{"id":"2109.10444","title":"Fairness-aware Class Imbalanced Learning","created":"2021-09-21","cited_by_count":19,"area":null},{"id":"2105.02778","title":"The Authors Matter: Understanding and Mitigating Implicit Bias in Deep Text Classification","created":"2021-05-06","cited_by_count":18,"area":null},{"id":"2205.15171","title":"Modular and On-demand Bias Mitigation with Attribute-Removal Subnetworks","created":"2022-05-30","cited_by_count":18,"area":null},{"id":"2102.00272","title":"EmpathBERT: A BERT-based Framework for Demographic-aware Empathy Prediction","created":"2021-01-30","cited_by_count":17,"area":null},{"id":"2111.03015","title":"Modeling Techniques for Machine Learning Fairness: A Survey","created":"2021-11-04","cited_by_count":17,"area":null},{"id":"2305.11386","title":"Improving Fairness in AI Models on Electronic Health Records: The Case for Federated Learning Methods","created":"2023-05-19","cited_by_count":17,"area":null},{"id":"2205.10095","title":"How to keep text private? A systematic review of deep learning methods for privacy-preserving natural language processing","created":"2022-05-20","cited_by_count":16,"area":null},{"id":"2104.07155","title":"Disentangling Representations of Text by Masking Transformers","created":"2021-04-14","cited_by_count":15,"area":null},{"id":"2107.09543","title":"Data synthesis and adversarial networks: A review and meta-analysis in cancer imaging","created":"2021-07-20","cited_by_count":15,"area":null},{"id":"2202.00035","title":"Learning Fair Representations via Rate-Distortion Maximization","created":"2022-01-31","cited_by_count":15,"area":null},{"id":"2109.08613","title":"Adversarial Scrubbing of Demographic Information for Text Classification","created":"2021-09-17","cited_by_count":14,"area":null},{"id":"2205.03589","title":"Learning Disentangled Textual Representations via Statistical Measures of Similarity","created":"2022-05-07","cited_by_count":14,"area":null},{"id":"2208.08176","title":"Visual Comparison of Language Model Adaptation","created":"2022-08-17","cited_by_count":14,"area":null},{"id":"2308.12539","title":"CALM : A Multi-task Benchmark for Comprehensive Assessment of Language Model Bias","created":"2023-08-24","cited_by_count":14,"area":null},{"id":"2105.04144","title":"Transitioning from Real to Synthetic data: Quantifying the bias in model","created":"2021-05-10","cited_by_count":12,"area":null},{"id":"2109.04624","title":"Style Pooling: Automatic Text Style Obfuscation for Improved Classification Fairness","created":"2021-09-10","cited_by_count":12,"area":null},{"id":"2204.09391","title":"You Are What You Write: Preserving Privacy in the Era of Large Language Models","created":"2022-04-20","cited_by_count":12,"area":null},{"id":"2208.08140","title":"Differential Privacy in Natural Language Processing: The Story So Far","created":"2022-08-17","cited_by_count":12,"area":null},{"id":"2309.01265","title":"SOAR: Scene-debiasing Open-set Action Recognition","created":"2023-09-03","cited_by_count":12,"area":null},{"id":"2205.10228","title":"You Don't Know My Favorite Color: Preventing Dialogue Representations from Revealing Speakers' Private Personas","created":"2022-04-26","cited_by_count":11,"area":null},{"id":"2205.11485","title":"Conditional Supervised Contrastive Learning for Fair Text Classification","created":"2022-05-23","cited_by_count":11,"area":null},{"id":"2302.05711","title":"Fair Enough: Standardizing Evaluation and Model Selection for Fairness Research in NLP","created":"2023-02-11","cited_by_count":11,"area":null},{"id":"2310.15398","title":"\"One-Size-Fits-All\"? Examining Expectations around What Constitute \"Fair\" or \"Good\" NLG System Behaviors","created":"2023-10-23","cited_by_count":11,"area":null},{"id":"2312.00194","title":"Robust Concept Erasure via Kernelized Rate-Distortion Maximization","created":"2023-11-30","cited_by_count":11,"area":null},{"id":"2411.10023","title":"Model Inversion Attacks: A Survey of Approaches and Countermeasures","created":"2024-11-15","cited_by_count":11,"area":null},{"id":"2101.06980","title":"Mitigating the Position Bias of Transformer Models in Passage Re-Ranking","created":"2021-01-18","cited_by_count":10,"area":null},{"id":"2205.10762","title":"How sensitive are translation systems to extra contexts? Mitigating gender bias in Neural Machine Translation models through relevant contexts","created":"2022-05-22","cited_by_count":10,"area":null},{"id":"2207.03444","title":"Fairness and Bias in Robot Learning","created":"2022-07-07","cited_by_count":10,"area":null},{"id":"2603.07368","title":"Position: LLMs Must Use Functor-Based and RAG-Driven Bias Mitigation for Fairness","created":"2026-03-07","cited_by_count":10,"area":null},{"id":"2104.08857","title":"Emotion-Regularized Conditional Variational Autoencoder for Emotional Response Generation","created":"2021-04-18","cited_by_count":9,"area":null},{"id":"2205.06135","title":"Fair NLP Models with Differentially Private Text Encoders","created":"2022-05-12","cited_by_count":9,"area":null},{"id":"2210.12587","title":"Model ensemble instead of prompt fusion: a sample-specific knowledge transfer method for few-shot prompt tuning","created":"2022-10-23","cited_by_count":9,"area":null},{"id":"2311.07115","title":"Gen-Z: Generative Zero-Shot Text Classification with Contextualized Label Descriptions","created":"2023-11-13","cited_by_count":9,"area":null},{"id":"2203.06317","title":"Towards Equal Opportunity Fairness through Adversarial Learning","created":"2022-03-12","cited_by_count":8,"area":null},{"id":"2206.10923","title":"FairGrad: Fairness Aware Gradient Descent","created":"2022-06-22","cited_by_count":8,"area":null},{"id":"2302.10701","title":"Scalable Infomin Learning","created":"2023-02-21","cited_by_count":8,"area":null},{"id":"2401.16457","title":"Effective Controllable Bias Mitigation for Classification and Retrieval using Gate Adapters","created":"2024-01-29","cited_by_count":8,"area":null},{"id":"2406.03749","title":"NAP^2: A Benchmark for Naturalness and Privacy-Preserving Text Rewriting by Learning from Human","created":"2024-06-06","cited_by_count":8,"area":null},{"id":"2103.01819","title":"The Rediscovery Hypothesis: Language Models Need to Meet Linguistics","created":"2021-03-02","cited_by_count":7,"area":null},{"id":"2210.04573","title":"HumSet: Dataset of Multilingual Information Extraction and Classification for Humanitarian Crisis Response","created":"2022-10-10","cited_by_count":7,"area":null},{"id":"2203.08979","title":"Speaker Information Can Guide Models to Better Inductive Biases: A Case Study On Predicting Code-Switching","created":"2022-03-16","cited_by_count":6,"area":null},{"id":"2205.09867","title":"Gender Bias in Meta-Embeddings","created":"2022-05-19","cited_by_count":6,"area":null},{"id":"2302.02997","title":"Erasure of Unaligned Attributes from Neural Representations","created":"2023-02-06","cited_by_count":6,"area":null},{"id":"2303.08403","title":"DualFair: Fair Representation Learning at Both Group and Individual Levels via Contrastive Self-supervision","created":"2023-03-15","cited_by_count":6,"area":null},{"id":"2310.11991","title":"Removing Spurious Concepts from Neural Network Representations via Joint Subspace Estimation","created":"2023-10-18","cited_by_count":6,"area":null},{"id":"2503.20098","title":"Fundamental Limits of Perfect Concept Erasure","created":"2025-03-25","cited_by_count":6,"area":null},{"id":"2107.01791","title":"Doing Good or Doing Right? Exploring the Weakness of Commonsense Causal Reasoning Models","created":"2021-07-05","cited_by_count":5,"area":null},{"id":"2208.12212","title":"Sustaining Fairness via Incremental Learning","created":"2022-08-25","cited_by_count":5,"area":null},{"id":"2404.08354","title":"PMB5: Gaining More Insight into Neural Semantic Parsing with Challenging Benchmarks","created":"2024-04-12","cited_by_count":5,"area":null},{"id":"2502.00156","title":"ALBAR: Adversarial Learning approach to mitigate Biases in Action Recognition","created":"2025-01-31","cited_by_count":5,"area":null},{"id":"2503.12536","title":"Debiasing Diffusion Model: Enhancing Fairness through Latent Representation Learning in Stable Diffusion Model","created":"2025-03-16","cited_by_count":5,"area":"diffusion"},{"id":"2507.15112","title":"Distributional Machine Unlearning via Selective Data Removal","created":"2025-07-20","cited_by_count":5,"area":"safety"},{"id":"2109.09133","title":"Preventing Author Profiling through Zero-Shot Multilingual Back-Translation","created":"2021-09-19","cited_by_count":4,"area":null},{"id":"2205.01876","title":"fairlib: A Unified Framework for Assessing and Improving Classification Fairness","created":"2022-05-04","cited_by_count":4,"area":null}],"next_cursor":"100"}