{"list":"other","total":102,"rows":[{"id":"2112.04359","title":"Ethical and social risks of harm from Language Models","created":"2021-12-08","cited_by_count":966},{"id":"2203.02053","title":"Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning","created":"2022-03-03","cited_by_count":561},{"id":"2108.04884","title":"Retiring Adult: New Datasets for Fair Machine Learning","created":"2021-08-10","cited_by_count":449},{"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},{"id":"2202.07922","title":"ZeroGen: Efficient Zero-shot Learning via Dataset Generation","created":"2022-02-16","cited_by_count":211},{"id":"2305.14930","title":"In-Context Impersonation Reveals Large Language Models' Strengths and Biases","created":"2023-05-24","cited_by_count":155},{"id":"2206.01347","title":"MultiHiertt: Numerical Reasoning over Multi Hierarchical Tabular and Textual Data","created":"2022-06-03","cited_by_count":121},{"id":"1908.09369","title":"On Measuring and Mitigating Biased Inferences of Word Embeddings","created":"2019-08-25","cited_by_count":112},{"id":"2110.12884","title":"DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networks","created":"2021-10-25","cited_by_count":109},{"id":"1911.09709","title":"Automatically Neutralizing Subjective Bias in Text","created":"2019-11-21","cited_by_count":105},{"id":"2109.03646","title":"Sustainable Modular Debiasing of Language Models","created":"2021-09-08","cited_by_count":100},{"id":"2204.03021","title":"The Moral Integrity Corpus: A Benchmark for Ethical Dialogue Systems","created":"2022-04-06","cited_by_count":93},{"id":"2204.08110","title":"Language Contamination Helps Explain the Cross-lingual Capabilities of English Pretrained Models","created":"2022-04-17","cited_by_count":92},{"id":"2211.13972","title":"Picking on the Same Person: Does Algorithmic Monoculture lead to Outcome Homogenization?","created":"2022-11-25","cited_by_count":91},{"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},{"id":"2203.15721","title":"On Decoding Strategies for Neural Text Generators","created":"2022-03-29","cited_by_count":90},{"id":"2109.05704","title":"Mitigating Language-Dependent Ethnic Bias in BERT","created":"2021-09-13","cited_by_count":87},{"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},{"id":"2104.14795","title":"Mitigating Political Bias in Language Models Through Reinforced Calibration","created":"2021-04-30","cited_by_count":73},{"id":"2002.10312","title":"Learning Certified Individually Fair Representations","created":"2020-02-24","cited_by_count":69},{"id":"2109.03858","title":"Collecting a Large-Scale Gender Bias Dataset for Coreference Resolution and Machine Translation","created":"2021-09-08","cited_by_count":62},{"id":"2104.07496","title":"Unmasking the Mask -- Evaluating Social Biases in Masked Language Models","created":"2021-04-15","cited_by_count":60},{"id":"2209.14557","title":"Neural Media Bias Detection Using Distant Supervision With BABE -- Bias Annotations By Experts","created":"2022-09-29","cited_by_count":56},{"id":"2210.02938","title":"Debiasing isn't enough! -- On the Effectiveness of Debiasing MLMs and their Social Biases in Downstream Tasks","created":"2022-10-06","cited_by_count":48},{"id":"2202.01034","title":"Diagnosing failures of fairness transfer across distribution shift in real-world medical settings","created":"2022-02-02","cited_by_count":45},{"id":"2206.03655","title":"pFL-Bench: A Comprehensive Benchmark for Personalized Federated Learning","created":"2022-06-08","cited_by_count":44},{"id":"2007.06699","title":"Fair Algorithms for Multi-Agent Multi-Armed Bandits","created":"2020-07-13","cited_by_count":41},{"id":"2203.08075","title":"Things not Written in Text: Exploring Spatial Commonsense from Visual Signals","created":"2022-03-15","cited_by_count":41},{"id":"2211.13358","title":"Turning the Tables: Biased, Imbalanced, Dynamic Tabular Datasets for ML Evaluation","created":"2022-11-24","cited_by_count":40},{"id":"2210.12529","title":"On-Demand Sampling: Learning Optimally from Multiple Distributions","created":"2022-10-22","cited_by_count":39},{"id":"2007.06029","title":"Ensuring Fairness Beyond the Training Data","created":"2020-07-12","cited_by_count":35},{"id":"2109.08253","title":"Balancing out Bias: Achieving Fairness Through Balanced Training","created":"2021-09-16","cited_by_count":34},{"id":"2210.08151","title":"ProtoVAE: A Trustworthy Self-Explainable Prototypical Variational Model","created":"2022-10-15","cited_by_count":34},{"id":"2109.06437","title":"Uncovering Implicit Gender Bias in Narratives through Commonsense Inference","created":"2021-09-14","cited_by_count":32},{"id":"2010.09851","title":"Can I Trust My Fairness Metric? Assessing Fairness with Unlabeled Data and Bayesian Inference","created":"2020-10-19","cited_by_count":31},{"id":"2210.14975","title":"MABEL: Attenuating Gender Bias using Textual Entailment Data","created":"2022-10-26","cited_by_count":31},{"id":"2109.10441","title":"Evaluating Debiasing Techniques for Intersectional Biases","created":"2021-09-21","cited_by_count":30},{"id":"2110.00521","title":"Unpacking the Interdependent Systems of Discrimination: Ableist Bias in NLP Systems through an Intersectional Lens","created":"2021-10-01","cited_by_count":30},{"id":"2201.12093","title":"PCL: Peer-Contrastive Learning with Diverse Augmentations for Unsupervised Sentence Embeddings","created":"2022-01-28","cited_by_count":29},{"id":"2206.00129","title":"Fairness Transferability Subject to Bounded Distribution Shift","created":"2022-05-31","cited_by_count":28},{"id":"2305.11262","title":"CHBias: Bias Evaluation and Mitigation of Chinese Conversational Language Models","created":"2023-05-18","cited_by_count":28},{"id":"2009.07503","title":"Minimize Exposure Bias of Seq2Seq Models in Joint Entity and Relation Extraction","created":"2020-09-16","cited_by_count":27},{"id":"2107.06720","title":"Fairness in Ranking under Uncertainty","created":"2021-07-14","cited_by_count":27},{"id":"2209.06970","title":"Generative Visual Prompt: Unifying Distributional Control of Pre-Trained Generative Models","created":"2022-09-14","cited_by_count":27},{"id":"2006.10221","title":"Fair Hierarchical Clustering","created":"2020-06-18","cited_by_count":25},{"id":"2011.03173","title":"Does enforcing fairness mitigate biases caused by subpopulation shift?","created":"2020-11-06","cited_by_count":25},{"id":"2112.04899","title":"Assessing Fairness in the Presence of Missing Data","created":"2021-12-07","cited_by_count":24},{"id":"2010.07431","title":"Fairness in Streaming Submodular Maximization: Algorithms and Hardness","created":"2020-10-14","cited_by_count":23},{"id":"2109.11708","title":"Detect and Perturb: Neutral Rewriting of Biased and Sensitive Text via Gradient-based Decoding","created":"2021-09-24","cited_by_count":23},{"id":"2206.03200","title":"FairVFL: A Fair Vertical Federated Learning Framework with Contrastive Adversarial Learning","created":"2022-06-07","cited_by_count":23},{"id":"2209.07735","title":"Enhance the Visual Representation via Discrete Adversarial Training","created":"2022-09-16","cited_by_count":23},{"id":"2211.02091","title":"Fairness in Federated Learning via Core-Stability","created":"2022-11-03","cited_by_count":23},{"id":"2106.07239","title":"Fair Clustering Under a Bounded Cost","created":"2021-06-14","cited_by_count":21},{"id":"2110.04363","title":"Certifying Robustness to Programmable Data Bias in Decision Trees","created":"2021-10-08","cited_by_count":21},{"id":"2206.12796","title":"Transferring Fairness under Distribution Shifts via Fair Consistency Regularization","created":"2022-06-26","cited_by_count":21},{"id":"2307.01595","title":"Prompt Tuning Pushes Farther, Contrastive Learning Pulls Closer: A Two-Stage Approach to Mitigate Social Biases","created":"2023-07-04","cited_by_count":21},{"id":"2112.07447","title":"Measuring Fairness with Biased Rulers: A Survey on Quantifying Biases in Pretrained Language Models","created":"2021-12-14","cited_by_count":20},{"id":"2205.13972","title":"Counterfactual Fairness with Partially Known Causal Graph","created":"2022-05-27","cited_by_count":20},{"id":"2305.19329","title":"Mitigating Test-Time Bias for Fair Image Retrieval","created":"2023-05-23","cited_by_count":20},{"id":"2010.10649","title":"Detecting Media Bias in News Articles using Gaussian Bias Distributions","created":"2020-10-20","cited_by_count":19},{"id":"2210.14424","title":"Geographic Citation Gaps in NLP Research","created":"2022-10-26","cited_by_count":19},{"id":"2204.04026","title":"Fair and Argumentative Language Modeling for Computational Argumentation","created":"2022-04-08","cited_by_count":18},{"id":"2210.07455","title":"Controlling Bias Exposure for Fair Interpretable Predictions","created":"2022-10-14","cited_by_count":18},{"id":"2008.01548","title":"Defining and Evaluating Fair Natural Language Generation","created":"2020-07-28","cited_by_count":17},{"id":"2106.03257","title":"Structured Reordering for Modeling Latent Alignments in Sequence Transduction","created":"2021-06-06","cited_by_count":17},{"id":"2211.17067","title":"Fair Ranking with Noisy Protected Attributes","created":"2022-11-30","cited_by_count":17},{"id":"2210.16079","title":"Debiasing Masks: A New Framework for Shortcut Mitigation in NLU","created":"2022-10-28","cited_by_count":16},{"id":"2202.00035","title":"Learning Fair Representations via Rate-Distortion Maximization","created":"2022-01-31","cited_by_count":15},{"id":"2109.04732","title":"Assessing the Reliability of Word Embedding Gender Bias Measures","created":"2021-09-10","cited_by_count":14},{"id":"2006.12732","title":"Fair Performance Metric Elicitation","created":"2020-06-23","cited_by_count":13},{"id":"2104.06483","title":"Can a Transformer Pass the Wug Test? Tuning Copying Bias in Neural Morphological Inflection Models","created":"2021-04-13","cited_by_count":13},{"id":"2205.00504","title":"Domain Adaptation meets Individual Fairness. And they get along","created":"2022-05-01","cited_by_count":13},{"id":"2207.03051","title":"A Large Scale Search Dataset for Unbiased Learning to Rank","created":"2022-07-07","cited_by_count":13},{"id":"2210.05153","title":"Understanding the Failure of Batch Normalization for Transformers in NLP","created":"2022-10-11","cited_by_count":12},{"id":"1911.10787","title":"A Causal Inference Method for Reducing Gender Bias in Word Embedding Relations","created":"2019-11-25","cited_by_count":11},{"id":"2010.15300","title":"Uncovering Latent Biases in Text: Method and Application to Peer Review","created":"2020-10-29","cited_by_count":11},{"id":"2109.02403","title":"Eliminating Sentiment Bias for Aspect-Level Sentiment Classification with Unsupervised Opinion Extraction","created":"2021-09-06","cited_by_count":11},{"id":"2112.05194","title":"Word Embeddings via Causal Inference: Gender Bias Reducing and Semantic Information Preserving","created":"2021-12-09","cited_by_count":11},{"id":"2210.06447","title":"Sampling in Constrained Domains with Orthogonal-Space Variational Gradient Descent","created":"2022-10-12","cited_by_count":11},{"id":"2004.03133","title":"Neutralizing Gender Bias in Word Embedding with Latent Disentanglement and Counterfactual Generation","created":"2020-04-07","cited_by_count":10},{"id":"2105.03714","title":"Consistency of Constrained Spectral Clustering under Graph Induced Fair Planted Partitions","created":"2021-05-08","cited_by_count":10},{"id":"2204.04440","title":"Are Two Heads the Same as One? Identifying Disparate Treatment in Fair Neural Networks","created":"2022-04-09","cited_by_count":10},{"id":"2209.09433","title":"Non-Linguistic Supervision for Contrastive Learning of Sentence Embeddings","created":"2022-09-20","cited_by_count":10},{"id":"2110.14286","title":"TopicNet: Semantic Graph-Guided Topic Discovery","created":"2021-10-27","cited_by_count":9},{"id":"2109.04399","title":"Gradual (In)Compatibility of Fairness Criteria","created":"2021-09-09","cited_by_count":8},{"id":"2203.11331","title":"On The Robustness of Offensive Language Classifiers","created":"2022-03-21","cited_by_count":8},{"id":"2204.03749","title":"Powering Finetuning in Few-Shot Learning: Domain-Agnostic Bias Reduction with Selected Sampling","created":"2022-04-07","cited_by_count":8},{"id":"2203.14349","title":"Reinforcement Guided Multi-Task Learning Framework for Low-Resource Stereotype Detection","created":"2022-03-27","cited_by_count":7},{"id":"2205.13346","title":"Keywords and Instances: A Hierarchical Contrastive Learning Framework Unifying Hybrid Granularities for Text Generation","created":"2022-05-26","cited_by_count":7},{"id":"2109.10697","title":"Towards Automatic Bias Detection in Knowledge Graphs","created":"2021-09-19","cited_by_count":6},{"id":"2111.05299","title":"Can Information Flows Suggest Targets for Interventions in Neural Circuits?","created":"2021-11-09","cited_by_count":6},{"id":"2209.10335","title":"Bias at a Second Glance: A Deep Dive into Bias for German Educational Peer-Review Data Modeling","created":"2022-09-21","cited_by_count":6},{"id":"2210.10689","title":"Towards Procedural Fairness: Uncovering Biases in How a Toxic Language Classifier Uses Sentiment Information","created":"2022-10-19","cited_by_count":6},{"id":"2005.06618","title":"Towards Socially Responsible AI: Cognitive Bias-Aware Multi-Objective Learning","created":"2020-05-14","cited_by_count":5},{"id":"2210.08362","title":"PAR: Political Actor Representation Learning with Social Context and Expert Knowledge","created":"2022-10-15","cited_by_count":5},{"id":"2211.03634","title":"No Word Embedding Model Is Perfect: Evaluating the Representation Accuracy for Social Bias in the Media","created":"2022-11-07","cited_by_count":5},{"id":"2201.12947","title":"Fair Wrapping for Black-box Predictions","created":"2022-01-31","cited_by_count":4},{"id":"2103.11795","title":"Simpson's Bias in NLP Training","created":"2021-03-13","cited_by_count":3},{"id":"2205.14798","title":"Random Rank: The One and Only Strategyproof and Proportionally Fair Randomized Facility Location Mechanism","created":"2022-05-30","cited_by_count":3},{"id":"2211.06569","title":"RISE: Robust Individualized Decision Learning with Sensitive Variables","created":"2022-11-12","cited_by_count":3}],"next_cursor":"100"}