{"total":75,"rows":[{"id":"2202.06539","title":"Deduplicating Training Data Mitigates Privacy Risks in Language Models","created":"2022-02-14","cited_by_count":314,"area":null},{"id":"2104.06001","title":"Gender Bias in Machine Translation","created":"2021-04-13","cited_by_count":117,"area":null},{"id":"2207.00220","title":"Pile of Law: Learning Responsible Data Filtering from the Law and a 256GB Open-Source Legal Dataset","created":"2022-07-01","cited_by_count":113,"area":null},{"id":"2101.09523","title":"Debiasing Pre-trained Contextualised Embeddings","created":"2021-01-23","cited_by_count":107,"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":"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":"2104.07504","title":"Natural Language Understanding with Privacy-Preserving BERT","created":"2021-04-15","cited_by_count":55,"area":null},{"id":"2101.10001","title":"Diverse Adversaries for Mitigating Bias in Training","created":"2021-01-25","cited_by_count":48,"area":null},{"id":"2109.06105","title":"NeuTral Rewriter: A Rule-Based and Neural Approach to Automatic Rewriting into Gender-Neutral Alternatives","created":"2021-09-13","cited_by_count":46,"area":null},{"id":"2202.08011","title":"Towards Identifying Social Bias in Dialog Systems: Frame, Datasets, and Benchmarks","created":"2022-02-16","cited_by_count":36,"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":"2201.00971","title":"Submix: Practical Private Prediction for Large-Scale Language Models","created":"2022-01-04","cited_by_count":31,"area":null},{"id":"2103.07567","title":"Privacy Regularization: Joint Privacy-Utility Optimization in Language Models","created":"2021-03-12","cited_by_count":30,"area":null},{"id":"2109.10441","title":"Evaluating Debiasing Techniques for Intersectional Biases","created":"2021-09-21","cited_by_count":30,"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":"2106.13973","title":"Benchmarking Differential Privacy and Federated Learning for BERT Models","created":"2021-06-26","cited_by_count":28,"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":"2101.09525","title":"Dictionary-based Debiasing of Pre-trained Word Embeddings","created":"2021-01-23","cited_by_count":24,"area":null},{"id":"2108.12318","title":"CAPE: Context-Aware Private Embeddings for Private Language Learning","created":"2021-08-27","cited_by_count":22,"area":null},{"id":"2205.02393","title":"Optimising Equal Opportunity Fairness in Model Training","created":"2022-05-05","cited_by_count":22,"area":null},{"id":"2102.09604","title":"Privacy-Preserving Graph Convolutional Networks for Text Classification","created":"2021-02-10","cited_by_count":19,"area":null},{"id":"2109.10444","title":"Fairness-aware Class Imbalanced Learning","created":"2021-09-21","cited_by_count":19,"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":"2106.03785","title":"Generative Adversarial Networks: A Survey Towards Private and Secure Applications","created":"2021-06-07","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":"2101.11310","title":"Adversarial Stylometry in the Wild: Transferable Lexical Substitution Attacks on Author Profiling","created":"2021-01-27","cited_by_count":13,"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":"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":"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":"2409.06741","title":"Generative AI for Requirements Engineering: A Systematic Literature Review","created":"2024-09-10","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":"2202.12138","title":"How reparametrization trick broke differentially-private text representation learning","created":"2022-02-24","cited_by_count":10,"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":"2210.02574","title":"Privacy-Preserving Text Classification on BERT Embeddings with Homomorphic Encryption","created":"2022-10-05","cited_by_count":9,"area":null},{"id":"2312.17242","title":"Learning to Generate Text in Arbitrary Writing Styles","created":"2023-12-28","cited_by_count":9,"area":null},{"id":"2105.10909","title":"Killing One Bird with Two Stones: Model Extraction and Attribute Inference Attacks against BERT-based APIs","created":"2021-05-23","cited_by_count":8,"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":"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":"2211.04281","title":"SocioProbe: What, When, and Where Language Models Learn about Sociodemographics","created":"2022-11-08","cited_by_count":7,"area":null},{"id":"2402.08227","title":"Privacy-Preserving Language Model Inference with Instance Obfuscation","created":"2024-02-13","cited_by_count":7,"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":"2104.11413","title":"Unsupervised Information Obfuscation for Split Inference of Neural Networks","created":"2021-04-23","cited_by_count":5,"area":null},{"id":"2111.15129","title":"Anonymization for Skeleton Action Recognition","created":"2021-11-30","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":"2205.01876","title":"fairlib: A Unified Framework for Assessing and Improving Classification Fairness","created":"2022-05-04","cited_by_count":4,"area":null},{"id":"2209.04022","title":"Privacy of Autonomous Vehicles: Risks, Protection Methods, and Future Directions","created":"2022-09-08","cited_by_count":4,"area":null},{"id":"2309.10551","title":"A Neighbourhood-Aware Differential Privacy Mechanism for Static Word Embeddings","created":"2023-09-19","cited_by_count":4,"area":null},{"id":"2404.00463","title":"Addressing Both Statistical and Causal Gender Fairness in NLP Models","created":"2024-03-30","cited_by_count":4,"area":null},{"id":"2504.17421","title":"Towards Harnessing the Collaborative Power of Large and Small Models for Domain Tasks","created":"2025-04-24","cited_by_count":4,"area":null},{"id":"2210.08758","title":"Systematic Evaluation of Predictive Fairness","created":"2022-10-17","cited_by_count":3,"area":null},{"id":"2403.16584","title":"Can Large Language Models (or Humans) Disentangle Text?","created":"2024-03-25","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":"2209.02022","title":"How Much User Context Do We Need? Privacy by Design in Mental Health NLP Application","created":"2022-09-05","cited_by_count":2,"area":null},{"id":"2405.14521","title":"Synthetic Data Generation for Intersectional Fairness by Leveraging Hierarchical Group Structure","created":"2024-05-23","cited_by_count":2,"area":null},{"id":"2601.02307","title":"Differential Privacy for Transformer Embeddings of Text with Nonparametric Variational Information Bottleneck","created":"2026-01-05","cited_by_count":2,"area":null},{"id":"2603.07529","title":"Obliviator Reveals the Cost of Nonlinear Guardedness in Concept Erasure","created":"2026-03-08","cited_by_count":2,"area":null},{"id":"2201.03004","title":"Privacy-aware Early Detection of COVID-19 through Adversarial Training","created":"2022-01-09","cited_by_count":1,"area":null},{"id":"2201.10986","title":"Twitter-Demographer: A Flow-based Tool to Enrich Twitter Data","created":"2022-01-26","cited_by_count":1,"area":null},{"id":"2305.12495","title":"Fair Without Leveling Down: A New Intersectional Fairness Definition","created":"2023-05-21","cited_by_count":1,"area":null},{"id":"2403.05700","title":"DADIT: A Dataset for Demographic Classification of Italian Twitter Users and a Comparison of Prediction Methods","created":"2024-03-08","cited_by_count":1,"area":null},{"id":"2407.01334","title":"Protecting Privacy in Classifiers by Token Manipulation","created":"2024-07-01","cited_by_count":1,"area":null},{"id":"2203.06512","title":"On Information Hiding in Natural Language Systems","created":"2022-03-12","cited_by_count":0,"area":null},{"id":"2403.16142","title":"What Happens to a Dataset Transformed by a Projection-based Concept Removal Method?","created":"2024-03-24","cited_by_count":0,"area":null},{"id":"2406.19642","title":"IDT: Dual-Task Adversarial Attacks for Privacy Protection","created":"2024-06-28","cited_by_count":0,"area":"safety"},{"id":"2407.19345","title":"Inference-Time Selective Debiasing to Enhance Fairness in Text Classification Models","created":"2024-07-27","cited_by_count":0,"area":null},{"id":"2408.05497","title":"MABR: Multilayer Adversarial Bias Removal Without Prior Bias Knowledge","created":"2024-08-10","cited_by_count":0,"area":null},{"id":"2608.29624","title":"PrivBench: A Holistic and Modular Benchmarking Platform for Evaluating Text-to-Text Privatization","created":"2026-08-30","cited_by_count":0,"area":null}],"next_cursor":null}