{"total":162,"rows":[{"id":"2304.05335","title":"Toxicity in ChatGPT: Analyzing Persona-assigned Language Models","created":"2023-04-11","cited_by_count":360,"area":null},{"id":"2103.00453","title":"Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP","created":"2021-02-28","cited_by_count":337,"area":null},{"id":"2106.13219","title":"Towards Understanding and Mitigating Social Biases in Language Models","created":"2021-06-24","cited_by_count":296,"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":"2208.03188","title":"BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage","created":"2022-08-05","cited_by_count":198,"area":null},{"id":"2308.14921","title":"Gender bias and stereotypes in Large Language Models","created":"2023-08-28","cited_by_count":187,"area":null},{"id":"2102.04130","title":"Bias Out-of-the-Box: An Empirical Analysis of Intersectional Occupational Biases in Popular Generative Language Models","created":"2021-02-08","cited_by_count":141,"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":"2201.05273","title":"Pretrained Language Models for Text Generation: A Survey","created":"2022-01-14","cited_by_count":122,"area":null},{"id":"2104.06001","title":"Gender Bias in Machine Translation","created":"2021-04-13","cited_by_count":117,"area":null},{"id":"2101.09523","title":"Debiasing Pre-trained Contextualised Embeddings","created":"2021-01-23","cited_by_count":107,"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":"2105.02732","title":"What's in the Box? A Preliminary Analysis of Undesirable Content in the Common Crawl Corpus","created":"2021-05-06","cited_by_count":80,"area":null},{"id":"2411.10915","title":"Bias in Large Language Models: Origin, Evaluation, and Mitigation","created":"2024-11-16","cited_by_count":77,"area":null},{"id":"2104.14795","title":"Mitigating Political Bias in Language Models Through Reinforced Calibration","created":"2021-04-30","cited_by_count":73,"area":null},{"id":"2110.08466","title":"On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark","created":"2021-10-16","cited_by_count":73,"area":null},{"id":"2401.05778","title":"Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems","created":"2024-01-11","cited_by_count":66,"area":null},{"id":"2205.02526","title":"Theories of \"Gender\" in NLP Bias Research","created":"2022-05-05","cited_by_count":62,"area":null},{"id":"2104.07496","title":"Unmasking the Mask -- Evaluating Social Biases in Masked Language Models","created":"2021-04-15","cited_by_count":60,"area":null},{"id":"2205.00551","title":"Gender Bias in Masked Language Models for Multiple Languages","created":"2022-05-01","cited_by_count":60,"area":null},{"id":"2101.09688","title":"Stereotype and Skew: Quantifying Gender Bias in Pre-trained and Fine-tuned Language Models","created":"2021-01-24","cited_by_count":57,"area":null},{"id":"2106.06052","title":"Dynaboard: An Evaluation-As-A-Service Platform for Holistic Next-Generation Benchmarking","created":"2021-05-21","cited_by_count":53,"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":"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,"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":"2210.06929","title":"On the Explainability of Natural Language Processing Deep Models","created":"2022-10-13","cited_by_count":38,"area":null},{"id":"2203.11852","title":"Representation Bias in Data: A Survey on Identification and Resolution Techniques","created":"2022-03-22","cited_by_count":37,"area":null},{"id":"2110.05367","title":"Improving Gender Fairness of Pre-Trained Language Models without Catastrophic Forgetting","created":"2021-10-11","cited_by_count":35,"area":null},{"id":"2403.00277","title":"Gender Bias in Large Language Models across Multiple Languages","created":"2024-03-01","cited_by_count":35,"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":"2408.03907","title":"Decoding Biases: Automated Methods and LLM Judges for Gender Bias Detection in Language Models","created":"2024-08-07","cited_by_count":33,"area":null},{"id":"2305.13862","title":"A Trip Towards Fairness: Bias and De-Biasing in Large Language Models","created":"2023-05-23","cited_by_count":32,"area":null},{"id":"2103.11320","title":"Lawyers are Dishonest? Quantifying Representational Harms in Commonsense Knowledge Resources","created":"2021-03-21","cited_by_count":30,"area":null},{"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,"area":null},{"id":"2304.10153","title":"On the Independence of Association Bias and Empirical Fairness in Language Models","created":"2023-04-20","cited_by_count":29,"area":null},{"id":"2106.00169","title":"Gender Bias Amplification During Speed-Quality Optimization in Neural Machine Translation","created":"2021-06-01","cited_by_count":28,"area":null},{"id":"2306.08158","title":"Sociodemographic Bias in Language Models: A Survey and Forward Path","created":"2023-06-13","cited_by_count":28,"area":null},{"id":"2105.05541","title":"Evaluating Gender Bias in Natural Language Inference","created":"2021-05-12","cited_by_count":27,"area":null},{"id":"2402.17954","title":"Twists, Humps, and Pebbles: Multilingual Speech Recognition Models Exhibit Gender Performance Gaps","created":"2024-02-28","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":"2406.03198","title":"The Impossibility of Fair LLMs","created":"2024-05-28","cited_by_count":22,"area":null},{"id":"2207.02463","title":"Gender Biases and Where to Find Them: Exploring Gender Bias in Pre-Trained Transformer-based Language Models Using Movement Pruning","created":"2022-07-06","cited_by_count":21,"area":null},{"id":"2211.05414","title":"ADEPT: A DEbiasing PrompT Framework","created":"2022-11-10","cited_by_count":21,"area":null},{"id":"2106.10826","title":"Does Robustness Improve Fairness? Approaching Fairness with Word Substitution Robustness Methods for Text Classification","created":"2021-06-21","cited_by_count":20,"area":null},{"id":"2110.10470","title":"Interpreting Deep Learning Models in Natural Language Processing: A Review","created":"2021-10-20","cited_by_count":19,"area":null},{"id":"2301.00395","title":"CORGI-PM: A Chinese Corpus For Gender Bias Probing and Mitigation","created":"2023-01-01","cited_by_count":19,"area":null},{"id":"2104.10662","title":"COVID-19 sentiment analysis via deep learning during the rise of novel cases","created":"2021-04-05","cited_by_count":18,"area":null},{"id":"2203.07523","title":"Sense Embeddings are also Biased--Evaluating Social Biases in Static and Contextualised Sense Embeddings","created":"2022-03-14","cited_by_count":18,"area":null},{"id":"2210.07455","title":"Controlling Bias Exposure for Fair Interpretable Predictions","created":"2022-10-14","cited_by_count":18,"area":null},{"id":"2212.04273","title":"Better Hit the Nail on the Head than Beat around the Bush: Removing Protected Attributes with a Single Projection","created":"2022-12-08","cited_by_count":17,"area":null},{"id":"2109.00545","title":"Fair Representation: Guaranteeing Approximate Multiple Group Fairness for Unknown Tasks","created":"2021-09-01","cited_by_count":16,"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":"2206.10744","title":"Don't Forget About Pronouns: Removing Gender Bias in Language Models Without Losing Factual Gender Information","created":"2022-06-21","cited_by_count":16,"area":null},{"id":"2207.10245","title":"The Birth of Bias: A case study on the evolution of gender bias in an English language model","created":"2022-07-21","cited_by_count":16,"area":null},{"id":"2406.02378","title":"On the Intrinsic Self-Correction Capability of LLMs: Uncertainty and Latent Concept","created":"2024-06-04","cited_by_count":16,"area":null},{"id":"2110.08413","title":"Invariant Language Modeling","created":"2021-10-16","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":"2405.11290","title":"MBIAS: Mitigating Bias in Large Language Models While Retaining Context","created":"2024-05-18","cited_by_count":15,"area":null},{"id":"2109.04732","title":"Assessing the Reliability of Word Embedding Gender Bias Measures","created":"2021-09-10","cited_by_count":14,"area":null},{"id":"2302.06975","title":"A Review of the Role of Causality in Developing Trustworthy AI Systems","created":"2023-02-14","cited_by_count":14,"area":null},{"id":"2310.10310","title":"Investigating Bias in Multilingual Language Models: Cross-Lingual Transfer of Debiasing Techniques","created":"2023-10-16","cited_by_count":14,"area":null},{"id":"2311.10395","title":"Bias A-head? Analyzing Bias in Transformer-Based Language Model Attention Heads","created":"2023-11-17","cited_by_count":14,"area":null},{"id":"2110.09216","title":"The Arabic Parallel Gender Corpus 2.0: Extensions and Analyses","created":"2021-10-18","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":"2302.13136","title":"Toward Fairness in Text Generation via Mutual Information Minimization based on Importance Sampling","created":"2023-02-25","cited_by_count":12,"area":null},{"id":"2307.04303","title":"Learning to Generate Equitable Text in Dialogue from Biased Training Data","created":"2023-07-10","cited_by_count":12,"area":null},{"id":"2307.10522","title":"Gender-tuning: Empowering Fine-tuning for Debiasing Pre-trained Language Models","created":"2023-07-20","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":"2412.11679","title":"Bias Vector: Mitigating Biases in Language Models with Task Arithmetic Approach","created":"2024-12-16","cited_by_count":12,"area":null},{"id":"2107.05987","title":"Generating Gender Augmented Data for NLP","created":"2021-07-13","cited_by_count":11,"area":null},{"id":"2110.14336","title":"Feature and Label Embedding Spaces Matter in Addressing Image Classifier Bias","created":"2021-10-27","cited_by_count":11,"area":null},{"id":"2112.05194","title":"Word Embeddings via Causal Inference: Gender Bias Reducing and Semantic Information Preserving","created":"2021-12-09","cited_by_count":11,"area":null},{"id":"2508.15830","title":"DAIQ: Auditing Demographic Attribute Inference from Question in LLMs","created":"2025-08-18","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":"2204.09591","title":"A Survey on Bias and Fairness in Natural Language Processing","created":"2022-03-06","cited_by_count":9,"area":null},{"id":"2303.05382","title":"ChatGPT is on the Horizon: Could a Large Language Model be Suitable for Intelligent Traffic Safety Research and Applications?","created":"2023-03-06","cited_by_count":9,"area":null},{"id":"2204.10365","title":"Towards an Enhanced Understanding of Bias in Pre-trained Neural Language Models: A Survey with Special Emphasis on Affective Bias","created":"2022-04-21","cited_by_count":8,"area":null},{"id":"2106.00181","title":"Gender Bias Hidden Behind Chinese Word Embeddings: The Case of Chinese Adjectives","created":"2021-06-01","cited_by_count":7,"area":null},{"id":"2205.02211","title":"User-Centric Gender Rewriting","created":"2022-05-04","cited_by_count":7,"area":null},{"id":"2212.11672","title":"Trustworthy Social Bias Measurement","created":"2022-12-20","cited_by_count":7,"area":null},{"id":"2302.02453","title":"FineDeb: A Debiasing Framework for Language Models","created":"2023-02-05","cited_by_count":7,"area":null},{"id":"2312.00554","title":"Questioning Biases in Case Judgment Summaries: Legal Datasets or Large Language Models?","created":"2023-12-01","cited_by_count":7,"area":null},{"id":"2109.14039","title":"Marked Attribute Bias in Natural Language Inference","created":"2021-09-28","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":"2209.08110","title":"Detecting Political Biases of Named Entities and Hashtags on Twitter","created":"2022-09-16","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":"2508.00709","title":"NyayaRAG: Realistic Legal Judgment Prediction with RAG under the Indian Common Law System","created":"2025-08-01","cited_by_count":6,"area":null},{"id":"2105.09047","title":"Obstructing Classification via Projection","created":"2021-05-19","cited_by_count":5,"area":null},{"id":"2110.15871","title":"From Theories on Styles to their Transfer in Text: Bridging the Gap with a Hierarchical Survey","created":"2021-10-29","cited_by_count":5,"area":null},{"id":"2204.00536","title":"Semi-FairVAE: Semi-supervised Fair Representation Learning with Adversarial Variational Autoencoder","created":"2022-04-01","cited_by_count":5,"area":null},{"id":"2306.07152","title":"Measuring Sentiment Bias in Machine Translation","created":"2023-06-12","cited_by_count":5,"area":null},{"id":"2405.06687","title":"Hire Me or Not? Examining Language Model's Behavior with Occupation Attributes","created":"2024-05-06","cited_by_count":5,"area":null},{"id":"2511.08225","title":"Benchmarking Educational LLMs with Analytics: A Case Study on Gender Bias in Feedback","created":"2025-11-11","cited_by_count":5,"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":"2312.06499","title":"TaCo: Targeted Concept Erasure Prevents Non-Linear Classifiers From Detecting Protected Attributes","created":"2023-12-11","cited_by_count":4,"area":null},{"id":"2503.06792","title":"On the Mutual Influence of Gender and Occupation in LLM Representations","created":"2025-03-09","cited_by_count":4,"area":null},{"id":"2504.03520","title":"Neutralizing the Narrative: AI-Powered Debiasing of Online News Articles","created":"2025-04-04","cited_by_count":4,"area":null},{"id":"2103.05841","title":"Interpretable bias mitigation for textual data: Reducing gender bias in patient notes while maintaining classification performance","created":"2021-03-10","cited_by_count":3,"area":null},{"id":"2104.02797","title":"VERB: Visualizing and Interpreting Bias Mitigation Techniques for Word Representations","created":"2021-04-06","cited_by_count":3,"area":null},{"id":"2109.14047","title":"Second Order WinoBias (SoWinoBias) Test Set for Latent Gender Bias Detection in Coreference Resolution","created":"2021-09-28","cited_by_count":3,"area":null}],"next_cursor":"100"}